quqxui/Awesome-LLM4IE-Papers

Awesome papers about generative Information Extraction (IE) using Large Language Models (LLMs)

1,064

64 commits

updated Nov 18, 2024

See the code

README

Awesome-LLM4IE-Papers

🔥🔥🔥 The article has been accepted by Frontiers of Computer Science (FCS).


Awesome papers about generative Information extraction using LLMs

The organization of papers is discussed in our survey: Large Language Models for Generative Information Extraction: A Survey.

If you find any relevant academic papers that have not been included in our research, please submit a request for an update. We welcome contributions from everyone.

If any suggestions or mistakes, please feel free to let us know via email at derongxu@mail.ustc.edu.cn and chenweicw@mail.ustc.edu.cn. We appreciate your feedback and help in improving our work.

If you find our survey useful for your research, please cite the following paper:

@article{xu2024large,
  title={Large language models for generative information extraction: A survey},
  author={Xu, Derong and Chen, Wei and Peng, Wenjun and Zhang, Chao and Xu, Tong and Zhao, Xiangyu and Wu, Xian and Zheng, Yefeng and Wang, Yang and Chen, Enhong},
  journal={Frontiers of Computer Science},
  volume={18},
  number={6},
  pages={186357},
  year={2024},
  publisher={Springer}
}

📒 Table of Contents

💡 News

  • Update Logs
    • The details can be find in ./update_new_papers_list.
    • 2024/09/04 Add 22 papers
    • 2024/06/06 Add 41 papers
    • 2024/03/30 Add 27 papers
    • 2024/03/29 Add 20 papers

Information Extraction tasks

A taxonomy by various tasks.

Named Entity Recognition

Models targeting only ner tasks.

Entity Typing

Entity Identification & Typing

PaperVenueDateCode
Granular Entity Mapper: Advancing Fine-grained Multimodal Named Entity Recognition and GroundingEMNLP Findings2024
Double-Checker: Large Language Model as a Checker for Few-shot Named Entity RecognitionEMNLP Findings2024GitHub
VerifiNER: Verification-augmented NER via Knowledge-grounded Reasoning with Large Language ModelsACL2024GitHub
ProgGen: Generating Named Entity Recognition Datasets Step-by-step with Self-Reflexive Large Language ModelsACL Findings2024GitHub
Rethinking Negative Instances for Generative Named Entity RecognitionACL Findings2024GitHub
LLMs as Bridges: Reformulating Grounded Multimodal Named Entity RecognitionACL Findings2024GitHub
RT: a Retrieving and Chain-of-Thought framework for few-shot medical named entity recognitionOthers2024-05GitHub
P-ICL: Point In-Context Learning for Named Entity Recognition with Large Language ModelsArxiv2024-06GitHub
Astro-NER -- Astronomy Named Entity Recognition: Is GPT a Good Domain Expert Annotator?Arxiv2024-05
Know-Adapter: Towards Knowledge-Aware Parameter-Efficient Transfer Learning for Few-shot Named Entity RecognitionCOLING2024
ToNER: Type-oriented Named Entity Recognition with Generative Language ModelCOLING2024
CHisIEC: An Information Extraction Corpus for Ancient Chinese HistoryCOLING2024GitHub
Astronomical Knowledge Entity Extraction in Astrophysics Journal Articles via Large Language ModelsOthers2024-04
LTNER: Large Language Model Tagging for Named Entity Recognition with Contextualized Entity MarkingArxiv2024-04GitHub
Enhancing Software-Related Information Extraction via Single-Choice Question Answering with Large Language ModelsOthers2024-04
Knowledge-Enriched Prompt for Low-Resource Named Entity RecognitionTALLIP2024-04
VANER: Leveraging Large Language Model for Versatile and Adaptive Biomedical Named Entity RecognitionArxiv2024-04GitHub
LLMs in Biomedicine: A study on clinical Named Entity RecognitionArxiv2024-04
Out of Sesame Street: A Study of Portuguese Legal Named Entity Recognition Through In-Context LearningResearchGate2024-04
Mining experimental data from Materials Science literature with Large Language Models: an evaluation studyArxiv2024-04GitHub
LinkNER: Linking Local Named Entity Recognition Models to Large Language Models using UncertaintyWWW2024
Self-Improving for Zero-Shot Named Entity Recognition with Large Language ModelsNAACL Short2024GitHub
On-the-fly Definition Augmentation of LLMs for Biomedical NERNAACL2024GitHub
MetaIE: Distilling a Meta Model from LLM for All Kinds of Information Extraction TasksArxiv2024-03GitHub
Distilling Named Entity Recognition Models for Endangered Species from Large Language ModelsArxiv2024-03
Augmenting NER Datasets with LLMs: Towards Automated and Refined AnnotationArxiv2024-03
ConsistNER: Towards Instructive NER Demonstrations for LLMs with the Consistency of Ontology and ContextAAAI2024
Embedded Named Entity Recognition using Probing ClassifiersArxiv2024-03GitHub
In-Context Learning for Few-Shot Nested Named Entity RecognitionArxiv2024-02
LLM-DA: Data Augmentation via Large Language Models for Few-Shot Named Entity RecognitionArxiv2024-02
Structured information extraction from scientific text with large language modelsNature Communications2024-02GitHub
NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated DataArxiv2024-02
A Simple but Effective Approach to Improve Structured Language Model Output for Information ExtractionArxiv2024-02
PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity RecognitionArxiv2024-02
Small Language Model Is a Good Guide for Large Language Model in Chinese Entity Relation ExtractionArxiv2024-02
C-ICL: Contrastive In-context Learning for Information ExtractionArxiv2024-02
UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity RecognitionICLR2024GitHub
Improving Large Language Models for Clinical Named Entity Recognition via Prompt EngineeringArxiv2024-01GitHub
2INER: Instructive and In-Context Learning on Few-Shot Named Entity RecognitionEMNLP Findings2023-12
In-context Learning for Few-shot Multimodal Named Entity RecognitionEMNLP Findings2023-12
Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!EMNLP Findings2023-12GitHub
Learning to Rank Context for Named Entity Recognition Using a Synthetic DatasetEMNLP2023-12GitHub
LLMaAA: Making Large Language Models as Active AnnotatorsEMNLP Findings2023-12GitHub
Prompting ChatGPT in MNER: Enhanced Multimodal Named Entity Recognition with Auxiliary Refined KnowledgeEMNLP Findings2023-12GitHub
GLiNER: Generalist Model for Named Entity Recognition using Bidirectional TransformerArxiv2023-11GitHub
GPT Struct Me: Probing GPT Models on Narrative Entity ExtractionWI-IAT2023-10GitHub
GPT-NER: Named Entity Recognition via Large Language ModelsArxiv2023-10GitHub
Prompt-NER: Zero-shot Named Entity Recognition in Astronomy Literature via Large Language ModelsArxiv2023-10
Inspire the Large Language Model by External Knowledge on BioMedical Named Entity RecognitionArxiv2023-09
One Model for All Domains: Collaborative Domain-Prefx Tuning for Cross-Domain NERIJCAI2023-09GitHub
Chain-of-Thought Prompt Distillation for Multimodal Named Entity Recognition and Multimodal Relation ExtractionArxiv2023-08
Learning In-context Learning for Named Entity Recognition ACL2023-07GitHub
Debiasing Generative Named Entity Recognition by Calibrating Sequence LikelihoodACL Short2023-07
Entity-to-Text based Data Augmentation for various Named Entity Recognition TasksACL Findings2023-07
Large Language Models as Instructors: A Study on Multilingual Clinical Entity ExtractionBioNLP2023-07GitHub
NAG-NER: a Unified Non-Autoregressive Generation Framework for Various NER TasksACL Industry2023-07
Unified Named Entity Recognition as Multi-Label Sequence GenerationIJCNN2023-06
PromptNER : Prompting For Named Entity RecognitionArxiv2023-06
Does Synthetic Data Generation of LLMs Help Clinical Text Mining?Arxiv2023-04
Unified Text Structuralization with Instruction-tuned Language ModelsArxiv2023-03
Structured information extraction from complex scientific text with fine-tuned large language modelsArxiv2022-12Demo
LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable PromptingCOLING2022-10GitHub
De-bias for generative extraction in unified NER taskACL2022-05
InstructionNER: A Multi-Task Instruction-Based Generative Framework for Few-shot NERArxiv2022-03
Document-level Entity-based Extraction as Template GenerationEMNLP2021-11GitHub
A Unified Generative Framework for Various NER SubtasksACL2021-08GitHub
Template-Based Named Entity Recognition Using BARTACL Findings2021-08GitHub

Relation Extraction

Models targeting only RE tasks.

Relation Classification

PaperVenueDateCode
Enhancing Software-Related Information Extraction via Single-Choice Question Answering with Large Language ModelsOthers2024-04
CRE-LLM: A Domain-Specific Chinese Relation Extraction Framework with Fine-tuned Large Language ModelArxiv2024-04GitHub
Recall, Retrieve and Reason: Towards Better In-Context Relation ExtractionIJCAI2024-04
Empirical Analysis of Dialogue Relation Extraction with Large Language ModelsIJCAI2024-04
Meta In-Context Learning Makes Large Language Models Better Zero and Few-Shot Relation ExtractorsIJCAI2024-04
Retrieval-Augmented Generation-based Relation ExtractionArxiv2024-04GitHub
Relation Extraction Using Large Language Models: A Case Study on Acupuncture Point LocationsArxiv2024-04
STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language ModelsAAAI2024-03
Grasping the Essentials: Tailoring Large Language Models for Zero-Shot Relation ExtractionArxiv2024-02
Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation ExtractionEMNLP Findings2023-12
GPT-RE: In-context Learning for Relation Extraction using Large Language ModelsEMNLP2023-12GitHub
Guideline Learning for In-context Information ExtractionEMNLP2023-12
Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!EMNLP Findings2023-12GitHub
LLMaAA: Making Large Language Models as Active AnnotatorsEMNLP Findings2023-12GitHub
Improving Unsupervised Relation Extraction by Augmenting Diverse Sentence PairsEMNLP2023-12GitHub
Revisiting Large Language Models as Zero-shot Relation ExtractorsEMNLP Findings2023-12
Mastering the Task of Open Information Extraction with Large Language Models and Consistent Reasoning EnvironmentArxiv2023-10
Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation ExtractorsACL Findings2023-07GitHub
How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?ACL Workshop2023-07GitHub
Sequence generation with label augmentation for relation extractionAAAI2023-06GitHub
Does Synthetic Data Generation of LLMs Help Clinical Text Mining?Arxiv2023-04
DORE: Document Ordered Relation Extraction based on Generative FrameworkEMNLP Findings2022-12
REBEL: Relation Extraction By End-to-end Language generationEMNLP Findings2021-11GitHub

Relation Triplet

Relation Strict

Event Extraction

Models targeting only EE tasks.

Event Detection

Event Argument Extraction

Event Detection & Argument Extraction

Universal Information Extraction

Unified models targeting multiple IE tasks.

NL-LLMs based

Code-LLMs based

Information Extraction Techniques

A taxonomy by techniques.

Supervised Fine-tuning

PaperVenueDateCode
Rethinking Negative Instances for Generative Named Entity RecognitionACL Findings2024GitHub
Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument ExtractionACL Findings2024GitHub
AutoRE: Document-Level Relation Extraction with Large Language ModelsACL Demos2024GitHub
Recall, Retrieve and Reason: Towards Better In-Context Relation ExtractionIJCAI2024-04
Empirical Analysis of Dialogue Relation Extraction with Large Language ModelsIJCAI2024-04
An Autoregressive Text-to-Graph Framework for Joint Entity and Relation ExtractionAAAI2024GitHub
Improving Recall of Large Language Models: A Model Collaboration Approach for Relational Triple ExtractionCOLING2024GitHub
ToNER: Type-oriented Named Entity Recognition with Generative Language ModelCOLING2024
CHisIEC: An Information Extraction Corpus for Ancient Chinese HistoryCOLING2024GitHub
KeyEE: Enhancing Low-Resource Generative Event Extraction with Auxiliary Keyword Sub-PromptOthers2024-04GitHub
VANER: Leveraging Large Language Model for Versatile and Adaptive Biomedical Named Entity RecognitionArxiv2024-04GitHub
LLMs in Biomedicine: A study on clinical Named Entity RecognitionArxiv2024-04
Mining experimental data from Materials Science literature with Large Language Models: an evaluation studyArxiv2024-04GitHub
CRE-LLM: A Domain-Specific Chinese Relation Extraction Framework with Fine-tuned Large Language ModelArxiv2024-04GitHub
Relation Extraction Using Large Language Models: A Case Study on Acupuncture Point LocationsArxiv2024-04
Improving Event Definition Following For Zero-Shot Event DetectionArxiv2024-03
Embedded Named Entity Recognition using Probing ClassifiersArxiv2024-03GitHub
EventRL: Enhancing Event Extraction with Outcome Supervision for Large Language ModelsArxiv2024-02
Structured information extraction from scientific text with large language modelsNature Communications2024-02GitHub
PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity RecognitionArxiv2024-02
UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity RecognitionICLR2024GitHub
GoLLIE: Annotation Guidelines improve Zero-Shot Information-ExtractionICLR2024GitHub
Set Learning for Generative Information ExtractionEMNLP2023-12
Efficient Data Learning for Open Information Extraction with Pre-trained Language ModelsEMNLP Findings2023-12
DemoSG: Demonstration-enhanced Schema-guided Generation for Low-resource Event ExtractionEMNLP Findings2023-12GitHub
Calibrated Seq2seq Models for Efficient and Generalizable Ultra-fine Entity TypingEMNLP Findings2023-12
GIELLM: Japanese General Information Extraction Large Language Model Utilizing Mutual Reinforcement EffectArxiv2023-11
GLiNER: Generalist Model for Named Entity Recognition using Bidirectional TransformerArxiv2023-11GitHub
Context-Aware Prompt for Generation-based Event Argument Extraction with Diffusion ModelsCIKM2023-10
Contextualized Soft Prompts for Extraction of Event ArgumentsACL Findings2023-07
AMPERE: AMR-Aware Prefix for Generation-Based Event Argument Extraction ModelACL2023-07GitHub
Debiasing Generative Named Entity Recognition by Calibrating Sequence LikelihoodACL short2023-07
DICE: Data-Efficient Clinical Event Extraction with Generative ModelsACL2023-07GitHub
Event Extraction as Question Generation and AnsweringACL short2023-07GitHub
NAG-NER: a Unified Non-Autoregressive Generation Framework for Various NER TasksACL Industry2023-07
Sequence generation with label augmentation for relation extractionAAAI2023-06GitHub
Unified Named Entity Recognition as Multi-Label Sequence GenerationIJCNN2023-06
InstructUIE: Multi-task Instruction Tuning for Unified Information ExtractionArxiv2023-04GitHub
Structured information extraction from complex scientific text with fine-tuned large language modelsArxiv2022-12Demo
Generative Entity Typing with Curriculum LearningEMNLP2022-12GitHub
DORE: Document Ordered Relation Extraction based on Generative FrameworkEMNLP Findings2022-12
LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language ModelNeurIPS2022-10GitHub
LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable PromptingCOLING2022-10GitHub
GenIE: Generative Information ExtractionNAACL2022-07GitHub
DEGREE: A Data-Efficient Generative Event Extraction ModelNAACL2022-07GitHub
ClarET: Pre-training a correlation-aware context-to-event transformer for event-centric generation and classificationACL2022-05GitHub
DEEPSTRUCT: Pretraining of Language Models for Structure PredictionACL Findings2022-05GitHub
Dynamic prefix-tuning for generative template-based event extractionACL2022-05
Prompt for extraction? PAIE: prompting argument interaction for event argument extractionACL2022-05GitHub
Unified Structure Generation for Universal Information ExtractionACL2022-05GitHub
De-bias for generative extraction in unified NER taskACL2022-05
Document-level Entity-based Extraction as Template GenerationEMNLP2021-11GitHub
REBEL: Relation Extraction By End-to-end Language generationEMNLP Findings2021-11GitHub
A Unified Generative Framework for Various NER SubtasksACL2021-08GitHub
Template-Based Named Entity Recognition Using BARTACL Findings2021-08GitHub
Text2event: Controllable sequence-to- structure generation for end-to-end event extractionACL2021-08GitHub
Document-level event argument extraction by conditional generationNAACL2021-06GitHub
Structured prediction as translation between augmented natural languagesICLR2021-01GitHub

Few-shot

Few-shot Fine-tuning

In-Context Learning

PaperVenueDateCode
TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event ExtractionACL Findings2024GitHub
RT: a Retrieving and Chain-of-Thought framework for few-shot medical named entity recognitionOthers2024-05GitHub
P-ICL: Point In-Context Learning for Named Entity Recognition with Large Language ModelsArxiv2024-06GitHub
LTNER: Large Language Model Tagging for Named Entity Recognition with Contextualized Entity MarkingArxiv2024-04GitHub
Enhancing Software-Related Information Extraction via Single-Choice Question Answering with Large Language ModelsOthers2024-04
LLMs in Biomedicine: A study on clinical Named Entity RecognitionArxiv2024-04
Out of Sesame Street: A Study of Portuguese Legal Named Entity Recognition Through In-Context LearningResearchGate2024-04
Mining experimental data from Materials Science literature with Large Language Models: an evaluation studyArxiv2024-04GitHub
Empirical Analysis of Dialogue Relation Extraction with Large Language ModelsIJCAI2024-04
Self-Improving for Zero-Shot Named Entity Recognition with Large Language ModelsNAACL Short2024GitHub
ConsistNER: Towards Instructive NER Demonstrations for LLMs with the Consistency of Ontology and ContextAAAI2024
On-the-fly Definition Augmentation of LLMs for Biomedical NERNAACL2024GitHub
CHisIEC: An Information Extraction Corpus for Ancient Chinese HistoryCOLING2024GitHub
Unlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple ExtractionCOLING2024
CodeKGC: Code Language Model for Generative Knowledge Graph ConstructionACM TALLIP2024-03GitHub
Document-Level In-Context Few-Shot Relation Extraction via Pre-Trained Language ModelsArxiv2024-02GitHub
In-Context Learning for Few-Shot Nested Named Entity RecognitionArxiv2024-02
Leveraging ChatGPT in Pharmacovigilance Event Extraction: An Empirical StudyEACL2024-02GitHub
Heuristic-Driven Link-of-Analogy Prompting: Enhancing Large Language Models for Document-Level Event Argument ExtractionArxiv2024-02
LinkNER: Linking Local Named Entity Recognition Models to Large Language Models using UncertaintyWWW2024
Small Language Model Is a Good Guide for Large Language Model in Chinese Entity Relation ExtractionArxiv2024-02
C-ICL: Contrastive In-context Learning for Information ExtractionArxiv2024-02
Improving Large Language Models for Clinical Named Entity Recognition via Prompt EngineeringArxiv2024-01GitHub
Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation ExtractionEMNLP Findings2023-12
GPT-RE: In-context Learning for Relation Extraction using Large Language ModelsEMNLP2023-12GitHub
Guideline Learning for In-context Information ExtractionEMNLP2023-12
Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!EMNLP Findings2023-12GitHub
Retrieval-Augmented Code Generation for Universal Information ExtractionArxiv2023-11
Mastering the Task of Open Information Extraction with Large Language Models and Consistent Reasoning EnvironmentArxiv2023-10
GPT-NER: Named Entity Recognition via Large Language ModelsArxiv2023-10GitHub
GPT Struct Me: Probing GPT Models on Narrative Entity ExtractionWI-IAT2023-10GitHub
Learning In-context Learning for Named Entity Recognition ACL2023-07GitHub
Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation ExtractorsACL Findings2023-07GitHub
Code4Struct: Code Generation for Few-Shot Event Structure PredictionACL2023-07GitHub
CODEIE: Large Code Generation Models are Better Few-Shot Information ExtractorsACL2023-07GitHub
How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?ACL Workshop2023-07GitHub
PromptNER : Prompting For Named Entity RecognitionArxiv2023-06GitHub
Unified Text Structuralization with Instruction-tuned Language ModelsArxiv2023-03

Zero-shot

Zero-shot Prompting

PaperVenueDateCode
ERA-CoT: Improving Chain-of-Thought through Entity Relationship AnalysisACL2024GitHub
Astronomical Knowledge Entity Extraction in Astrophysics Journal Articles via Large Language ModelsOthers2024-04
Mining experimental data from Materials Science literature with Large Language Models: an evaluation studyArxiv2024-04GitHub
Empirical Analysis of Dialogue Relation Extraction with Large Language ModelsIJCAI2024-04
Retrieval-Augmented Generation-based Relation ExtractionArxiv2024-04GitHub
Relation Extraction Using Large Language Models: A Case Study on Acupuncture Point LocationsArxiv2024-04
Meta In-Context Learning Makes Large Language Models Better Zero and Few-Shot Relation ExtractorsIJCAI2024-04
Self-Improving for Zero-Shot Named Entity Recognition with Large Language ModelsNAACL Short2024GitHub
CodeKGC: Code Language Model for Generative Knowledge Graph ConstructionACM TALLIP2024-03GitHub
On-the-fly Definition Augmentation of LLMs for Biomedical NERNAACL2024-03GitHub
Leveraging ChatGPT in Pharmacovigilance Event Extraction: An Empirical StudyEACL2024-02GitHub
A Simple but Effective Approach to Improve Structured Language Model Output for Information ExtractionArxiv2024-02
Small Language Model Is a Good Guide for Large Language Model in Chinese Entity Relation ExtractionArxiv2024-02
Improving Large Language Models for Clinical Named Entity Recognition via Prompt EngineeringArxiv2024-01GitHub
Improving Unsupervised Relation Extraction by Augmenting Diverse Sentence PairsEMNLP2023-12GitHub
Prompt-NER: Zero-shot Named Entity Recognition in Astronomy Literature via Large Language ModelsArxiv2023-10
Revisiting Large Language Models as Zero-shot Relation ExtractorsEMNLP Findings2023-10
Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation ExtractorsACL Findings2023-07GitHub
Code4Struct: Code Generation for Few-Shot Event Structure PredictionACL2023-07GitHub
A Monte Carlo Language Model Pipeline for Zero-Shot Sociopolitical Event ExtractionNeurIPS Workshop2023-10
Global Constraints with Prompting for Zero-Shot Event Argument ClassificationEACL Findings2023-05
Zero-Shot Information Extraction via Chatting with ChatGPTArxiv2023-02GitHub

Cross-Domain Learning

Cross-Type Learning

Data Augmentation

Data Annotation

Knowledge Retrieval

Inverse Generation

Synthetic Datasets for Instruction-tuning

Prompts Design

Question Answer

Chain of Thought

Self-Improvement

Constrained Decoding Generation

Specific Domain

PaperDomainVenueDateCode
Granular Entity Mapper: Advancing Fine-grained Multimodal Named Entity Recognition and GroundingMultimodalEMNLP Findings2024
LLMs as Bridges: Reformulating Grounded Multimodal Named Entity RecognitionMultimodalACL Findings2024GitHub
RT: a Retrieving and Chain-of-Thought framework for few-shot medical named entity recognitionMedicalOthers2024-05GitHub
Astro-NER -- Astronomy Named Entity Recognition: Is GPT a Good Domain Expert Annotator?AstronomyArxiv2024-05
Astronomical Knowledge Entity Extraction in Astrophysics Journal Articles via Large Language ModelsAstronomyOthers2024-04
VANER: Leveraging Large Language Model for Versatile and Adaptive Biomedical Named Entity RecognitionBiomedicalArxiv2024-04GitHub
LLMs in Biomedicine: A study on clinical Named Entity RecognitionBiomedicalArxiv2024-04
Enhancing Software-Related Information Extraction via Single-Choice Question Answering with Large Language ModelsSoftwareOthers2024-04
Out of Sesame Street: A Study of Portuguese Legal Named Entity Recognition Through In-Context LearningLegalResearchGate2024-04
Mining experimental data from Materials Science literature with Large Language Models: an evaluation studyScientificArxiv2024-04GitHub
Relation Extraction Using Large Language Models: A Case Study on Acupuncture Point LocationsAcupuncture PointArxiv2024-04
Advancing Entity Recognition in Biomedicine via Instruction Tuning of Large Language ModelsBiomedicalBioinformatics2024-03GitHub
Distilling Named Entity Recognition Models for Endangered Species from Large Language ModelsEndangered SpeciesArxiv2024-03
CHisIEC: An Information Extraction Corpus for Ancient Chinese HistoryHistoricalCOLING2024-03GitHub
On-the-fly Definition Augmentation of LLMs for Biomedical NERBiomedicalNAACL2024-03GitHub
Improving LLM-Based Health Information Extraction with In-Context LearningHealthOthers2024-03
Structured information extraction from scientific text with large language modelsScientificNat. Commun.2024-02GitHub
Leveraging ChatGPT in Pharmacovigilance Event Extraction: An Empirical StudyPharmacovigilanceEACL2024-02GitHub
Structured information extraction from scientific text with large language modelsScientificNat. Commun.2024-02GitHub
Combining prompt‑based language models and weak supervision for labeling named entity recognition on legal documentsLegalOthers2024-02
Improving Large Language Models for Clinical Named Entity Recognition via Prompt EngineeringClinicalArxiv2024-01GitHub
Impact of Sample Selection on In-Context Learning for Entity Extraction from Scientific WritingScientificEMNLP Findings2023-12GitHub
Prompting ChatGPT in MNER: Enhanced Multimodal Named Entity Recognition with Auxiliary Refined KnowledgeMultimodalENMLP Findings2023-12GitHub
In-context Learning for Few-shot Multimodal Named Entity RecognitionMultimodalENMLP Findings2023-12
PolyIE: A Dataset of Information Extraction from Polymer Material Scientific LiteraturePolymer MaterialArxiv2023-11GitHub
Prompt-NER: Zero-shot Named Entity Recognition in Astronomy Literature via Large Language ModelsAstronomicalArxiv2023-10
Inspire the Large Language Model by External Knowledge on BioMedical Named Entity RecognitionBiomedicalArxiv2023-09
Chain-of-Thought Prompt Distillation for Multimodal Named Entity Recognition and Multimodal Relation ExtractionMultimodalArxiv2023-08
DICE: Data-Efficient Clinical Event Extraction with Generative ModelsClinicalACL2023-07GitHub
How far is Language Model from 100% Few-shot Named Entity Recognition in Medical DomainMedicalArxiv2023-07GitHub
Large Language Models as Instructors: A Study on Multilingual Clinical Entity ExtractionMultilingual / ClinicalBioNLP2023-07GitHub
Does Synthetic Data Generation of LLMs Help Clinical Text Mining?ClinicalArxiv2023-04
Yes but.. Can ChatGPT Identify Entities in Historical DocumentsHistoricalJCDL2023-03
Zero-shot Clinical Entity Recognition using ChatGPTClinicalArxiv2023-03
Structured information extraction from complex scientific text with fine-tuned large language modelsScientificArxiv2022-12Demo
Multilingual generative language models for zero-shot cross-lingual event argument extractionMultilingualACL2022-05GitHub

Evaluation and Analysis

PaperVenueDateCode
TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event ExtractionACL Findings2024GitHub
IEPile: Unearthing Large-Scale Schema-Based Information Extraction CorpusACL Short2024GitHub
CHisIEC: An Information Extraction Corpus for Ancient Chinese HistoryCOLING2024GitHub
GenRES: Rethinking Evaluation for Generative Relation Extraction in the Era of Large Language ModelsNAACL2024GitHub
Empirical Analysis of Dialogue Relation Extraction with Large Language ModelsIJCAI2024
Astro-NER -- Astronomy Named Entity Recognition: Is GPT a Good Domain Expert Annotator?Arxiv2024-05
Relation Extraction Using Large Language Models: A Case Study on Acupuncture Point LocationsArxiv2024-04
Mining experimental data from Materials Science literature with Large Language Models: an evaluation studyArxiv2024-04GitHub
Distilling Named Entity Recognition Models for Endangered Species from Large Language ModelsArxiv2024-03
LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future OpportunitiesArxiv2024-02GitHub
Few shot clinical entity recognition in three languages: Masked language models outperform LLM promptingArxiv2024-02
Information Extraction from Legal Wills: How Well Does GPT-4 Do?EMNLP Findings2023-12GitHub
Information Extraction in Low-Resource Scenarios: Survey and PerspectiveArxiv2023-12GitHub
Empirical Study of Zero-Shot NER with ChatGPTEMNLP2023-12GitHub
NERetrieve: Dataset for Next Generation Named Entity Recognition and RetrievalEMNLP Findings2023-12GitHub
Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information ExtractionEMNLP2023-12GitHub
PolyIE: A Dataset of Information Extraction from Polymer Material Scientific LiteratureArxiv2023-11GitHub
XNLP: An Interactive Demonstration System for Universal Structured NLPArxiv2023-08Demo
A Zero-shot and Few-shot Study of Instruction-Finetuned Large Language Models Applied to Clinical and Biomedical TasksArxiv2023-07
How far is Language Model from 100% Few-shot Named Entity Recognition in Medical DomainArxiv2023-07GitHub
Revisiting Relation Extraction in the era of Large Language ModelsACL2023-07GitHub
Zero-shot Temporal Relation Extraction with ChatGPTBioNLP2023-07
InstructIE: A Chinese Instruction-based Information Extraction DatasetArxiv2023-05GitHub
Is Information Extraction Solved by ChatGPT? An Analysis of Performance, Evaluation Criteria, Robustness and ErrorsArxiv2023-05GitHub
Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and FaithfulnessArxiv2023-04GitHub
Exploring the Feasibility of ChatGPT for Event ExtractionArxiv2023-03
Yes but.. Can ChatGPT Identify Entities in Historical DocumentsJCDL2023-03
Zero-shot Clinical Entity Recognition using ChatGPTArxiv2023-03
Thinking about GPT-3 In-Context Learning for Biomedical IE? Think AgainEMNLP Findings2022-12GitHub
Large Language Models are Few-Shot Clinical Information ExtractorsEMNLP2022-12Huggingface

Project and Toolkit

Recently Updated Papers

2024/09/04

PaperVenueDateCode
Timeline-based Sentence Decomposition with In-Context Learning for Temporal Fact ExtractionACL2024-08GitHub
Epidemic Information Extraction for Event-Based Surveillance using Large Language ModelsICICT2024-08
SpeechEE: A Novel Benchmark for Speech Event ExtractionACM MM2024-08GitHub
HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information ExtractionArxiv2024-08
Knowledge AI: Fine-tuning NLP Models for Facilitating Scientific Knowledge Extraction and UnderstandingArxiv2024-08
Target Prompting for Information Extraction with Vision Language ModelArxiv2024-08
Evaluating Named Entity Recognition Using Few-Shot Prompting with Large Language ModelsArxiv2024-08GitHub
Utilizing Large Language Models for Named Entity Recognition in Traditional Chinese Medicine against COVID-19 Literature: Comparative StudyArxiv2024-08
CLLMFS: A Contrastive Learning enhanced Large Language Model Framework for Few-Shot Named Entity RecognitionECAI2024-08
LLMs are not Zero-Shot Reasoners for Biomedical Information ExtractionArxiv2024-08
Label Alignment and Reassignment with Generalist Large Language Model for Enhanced Cross-Domain Named Entity RecognitionArxiv2024-07
MMM: Multilingual Mutual Reinforcement Effect Mix Datasets & Test with Open-domain Information Extraction Large Language ModelsArxiv2024-08GitHub
FsPONER: Few-shot Prompt Optimization for Named Entity Recognition in Domain-specific ScenariosECAI2024-07GitHub
Adapting Multilingual LLMs to Low-Resource Languages with Knowledge Graphs via AdaptersKaLLM workshop2024-07GitHub
Show Less, Instruct More: Enriching Prompts with Definitions and Guidelines for Zero-Shot NERArxiv2024-07
Large Language Models Struggle in Token-Level Clinical Named Entity RecognitionAMIA2024-08
GLiNER multi-task: Generalist Lightweight Model for Various Information Extraction TasksArxiv2024-08
Retrieval Augmented Instruction Tuning for Open NER with Large Language ModelsArxiv2024-06GitHub
Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity RecognitionArxiv2024-06GitHub
Fighting Against the Repetitive Training and Sample Dependency Problem in Few-shot Named Entity RecognitionIEEE Access2024-06GitHub
llmNER: (Zero|Few)-Shot Named Entity Recognition, Exploiting the Power of Large Language ModelsArxiv2024-06GitHub
Assessing the Performance of Chinese Open Source Large Language Models in Information Extraction TasksArxiv2024-06

Datasets

* denotes the dataset is multimodal. # refers to the number of categories or sentences.

TaskDatasetDomain#Class#Train#Val#TestLink
NERACE04News76202745812Link
ACE05News772999711060Link
BC5CDRBiomedical2456045814797Link
Broad Twitter CorpusSocial Media3633810012000Link
CADECBiomedical1534010971160Link
CoNLL03News41404132503453Link
CoNLLppNews41404132503453Link
CrossNER-AIArtificial Intelligence14100350431Link
CrossNER-LiteratureLiterary12100400416
CrossNER-MusicMusical13100380465
CrossNER-PoliticsPolitical9199540650
CrossNER-ScienceScientific17200450543
FabNERScientific12943521822064Link
Few-NERDGeneral661317671882437468Link
FindVehicleTraffic21215652077720777Link
GENIABiomedical51502316691854Link
HarveyNERSocial Media4396713011303Link
MIT-MovieSocial Media12977424422442Link
MIT-RestaurantSocial Media8765915201520Link
MultiNERDWikipedia161341441000010000Link
NCBIBiomedical45432923940Link
OntoNotes 5.0General185992485288262Link
ShARe13Biomedical18508120509009Link
ShARe14Biomedical117404136015850Link
SNAP*Social Media4429014321459Link
Temporal Twitter Corpus (TTC)Social Meida3100005001500Link
Tweebank-NERSocial Media416397101201Link
Twitter2015*Social Media4400010003357Link
Twitter2017*Social Media43373723723Link
TwitterNER7Social Media77111886576Link
WikiDiverse*News136312755757Link
WNUT2017Social Media6339410091287Link
REACE05News71005124202050Link
ADEBiomedical13417427428Link
CoNLL04News5922231288Link
DocREDWikipedia963008300700Link
MNRE*Social Media231224716241614Link
NYTNews245619650005000Link
Re-TACREDNews40584651958413418Link
SciERCScientific71366187397Link
SemEval2010General19650714932717Link
TACREDNews42681242263115509Link
TACREVNews42681242263115509Link
EEACE05News33/2217172923832Link
CASIECybersecurity5/261118917783208Link
GENIA11Biomedical9/11873010911092Link
GENIA13Biomedical13/74000500500Link
PHEEBiomedical2/162898961968Link
RAMSNews139/657329924871Link
WikiEventsWikipedia50/595262378492Link

Star History

Star History Chart

cross-domain-learning
data-augmentation
event-arguments
event-detection
event-extraction
few-shot-learning
in-context-learning
information-extraction
knowledge-graph-construction
large-language-models
named-entity-recognition
relation-extraction
zero-shot-learning

Significant stargazers

Donatas Remeika

19 followers · starred Apr 2024

Nilanjan De

33 followers · starred Jan 2024

quqxui/Awesome-LLM4IE-Papers

Awesome papers about generative Information Extraction (IE) using Large Language Models (LLMs)

1,064

64 commits

updated Nov 18, 2024

See the code

README

Awesome-LLM4IE-Papers

🔥🔥🔥 The article has been accepted by Frontiers of Computer Science (FCS).


Awesome papers about generative Information extraction using LLMs

The organization of papers is discussed in our survey: Large Language Models for Generative Information Extraction: A Survey.

If you find any relevant academic papers that have not been included in our research, please submit a request for an update. We welcome contributions from everyone.

If any suggestions or mistakes, please feel free to let us know via email at derongxu@mail.ustc.edu.cn and chenweicw@mail.ustc.edu.cn. We appreciate your feedback and help in improving our work.

If you find our survey useful for your research, please cite the following paper:

@article{xu2024large,
  title={Large language models for generative information extraction: A survey},
  author={Xu, Derong and Chen, Wei and Peng, Wenjun and Zhang, Chao and Xu, Tong and Zhao, Xiangyu and Wu, Xian and Zheng, Yefeng and Wang, Yang and Chen, Enhong},
  journal={Frontiers of Computer Science},
  volume={18},
  number={6},
  pages={186357},
  year={2024},
  publisher={Springer}
}

📒 Table of Contents

💡 News

  • Update Logs
    • The details can be find in ./update_new_papers_list.
    • 2024/09/04 Add 22 papers
    • 2024/06/06 Add 41 papers
    • 2024/03/30 Add 27 papers
    • 2024/03/29 Add 20 papers

Information Extraction tasks

A taxonomy by various tasks.

Named Entity Recognition

Models targeting only ner tasks.

Entity Typing

Entity Identification & Typing

PaperVenueDateCode
Granular Entity Mapper: Advancing Fine-grained Multimodal Named Entity Recognition and GroundingEMNLP Findings2024
Double-Checker: Large Language Model as a Checker for Few-shot Named Entity RecognitionEMNLP Findings2024GitHub
VerifiNER: Verification-augmented NER via Knowledge-grounded Reasoning with Large Language ModelsACL2024GitHub
ProgGen: Generating Named Entity Recognition Datasets Step-by-step with Self-Reflexive Large Language ModelsACL Findings2024GitHub
Rethinking Negative Instances for Generative Named Entity RecognitionACL Findings2024GitHub
LLMs as Bridges: Reformulating Grounded Multimodal Named Entity RecognitionACL Findings2024GitHub
RT: a Retrieving and Chain-of-Thought framework for few-shot medical named entity recognitionOthers2024-05GitHub
P-ICL: Point In-Context Learning for Named Entity Recognition with Large Language ModelsArxiv2024-06GitHub
Astro-NER -- Astronomy Named Entity Recognition: Is GPT a Good Domain Expert Annotator?Arxiv2024-05
Know-Adapter: Towards Knowledge-Aware Parameter-Efficient Transfer Learning for Few-shot Named Entity RecognitionCOLING2024
ToNER: Type-oriented Named Entity Recognition with Generative Language ModelCOLING2024
CHisIEC: An Information Extraction Corpus for Ancient Chinese HistoryCOLING2024GitHub
Astronomical Knowledge Entity Extraction in Astrophysics Journal Articles via Large Language ModelsOthers2024-04
LTNER: Large Language Model Tagging for Named Entity Recognition with Contextualized Entity MarkingArxiv2024-04GitHub
Enhancing Software-Related Information Extraction via Single-Choice Question Answering with Large Language ModelsOthers2024-04
Knowledge-Enriched Prompt for Low-Resource Named Entity RecognitionTALLIP2024-04
VANER: Leveraging Large Language Model for Versatile and Adaptive Biomedical Named Entity RecognitionArxiv2024-04GitHub
LLMs in Biomedicine: A study on clinical Named Entity RecognitionArxiv2024-04
Out of Sesame Street: A Study of Portuguese Legal Named Entity Recognition Through In-Context LearningResearchGate2024-04
Mining experimental data from Materials Science literature with Large Language Models: an evaluation studyArxiv2024-04GitHub
LinkNER: Linking Local Named Entity Recognition Models to Large Language Models using UncertaintyWWW2024
Self-Improving for Zero-Shot Named Entity Recognition with Large Language ModelsNAACL Short2024GitHub
On-the-fly Definition Augmentation of LLMs for Biomedical NERNAACL2024GitHub
MetaIE: Distilling a Meta Model from LLM for All Kinds of Information Extraction TasksArxiv2024-03GitHub
Distilling Named Entity Recognition Models for Endangered Species from Large Language ModelsArxiv2024-03
Augmenting NER Datasets with LLMs: Towards Automated and Refined AnnotationArxiv2024-03
ConsistNER: Towards Instructive NER Demonstrations for LLMs with the Consistency of Ontology and ContextAAAI2024
Embedded Named Entity Recognition using Probing ClassifiersArxiv2024-03GitHub
In-Context Learning for Few-Shot Nested Named Entity RecognitionArxiv2024-02
LLM-DA: Data Augmentation via Large Language Models for Few-Shot Named Entity RecognitionArxiv2024-02
Structured information extraction from scientific text with large language modelsNature Communications2024-02GitHub
NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated DataArxiv2024-02
A Simple but Effective Approach to Improve Structured Language Model Output for Information ExtractionArxiv2024-02
PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity RecognitionArxiv2024-02
Small Language Model Is a Good Guide for Large Language Model in Chinese Entity Relation ExtractionArxiv2024-02
C-ICL: Contrastive In-context Learning for Information ExtractionArxiv2024-02
UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity RecognitionICLR2024GitHub
Improving Large Language Models for Clinical Named Entity Recognition via Prompt EngineeringArxiv2024-01GitHub
2INER: Instructive and In-Context Learning on Few-Shot Named Entity RecognitionEMNLP Findings2023-12
In-context Learning for Few-shot Multimodal Named Entity RecognitionEMNLP Findings2023-12
Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!EMNLP Findings2023-12GitHub
Learning to Rank Context for Named Entity Recognition Using a Synthetic DatasetEMNLP2023-12GitHub
LLMaAA: Making Large Language Models as Active AnnotatorsEMNLP Findings2023-12GitHub
Prompting ChatGPT in MNER: Enhanced Multimodal Named Entity Recognition with Auxiliary Refined KnowledgeEMNLP Findings2023-12GitHub
GLiNER: Generalist Model for Named Entity Recognition using Bidirectional TransformerArxiv2023-11GitHub
GPT Struct Me: Probing GPT Models on Narrative Entity ExtractionWI-IAT2023-10GitHub
GPT-NER: Named Entity Recognition via Large Language ModelsArxiv2023-10GitHub
Prompt-NER: Zero-shot Named Entity Recognition in Astronomy Literature via Large Language ModelsArxiv2023-10
Inspire the Large Language Model by External Knowledge on BioMedical Named Entity RecognitionArxiv2023-09
One Model for All Domains: Collaborative Domain-Prefx Tuning for Cross-Domain NERIJCAI2023-09GitHub
Chain-of-Thought Prompt Distillation for Multimodal Named Entity Recognition and Multimodal Relation ExtractionArxiv2023-08
Learning In-context Learning for Named Entity Recognition ACL2023-07GitHub
Debiasing Generative Named Entity Recognition by Calibrating Sequence LikelihoodACL Short2023-07
Entity-to-Text based Data Augmentation for various Named Entity Recognition TasksACL Findings2023-07
Large Language Models as Instructors: A Study on Multilingual Clinical Entity ExtractionBioNLP2023-07GitHub
NAG-NER: a Unified Non-Autoregressive Generation Framework for Various NER TasksACL Industry2023-07
Unified Named Entity Recognition as Multi-Label Sequence GenerationIJCNN2023-06
PromptNER : Prompting For Named Entity RecognitionArxiv2023-06
Does Synthetic Data Generation of LLMs Help Clinical Text Mining?Arxiv2023-04
Unified Text Structuralization with Instruction-tuned Language ModelsArxiv2023-03
Structured information extraction from complex scientific text with fine-tuned large language modelsArxiv2022-12Demo
LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable PromptingCOLING2022-10GitHub
De-bias for generative extraction in unified NER taskACL2022-05
InstructionNER: A Multi-Task Instruction-Based Generative Framework for Few-shot NERArxiv2022-03
Document-level Entity-based Extraction as Template GenerationEMNLP2021-11GitHub
A Unified Generative Framework for Various NER SubtasksACL2021-08GitHub
Template-Based Named Entity Recognition Using BARTACL Findings2021-08GitHub

Relation Extraction

Models targeting only RE tasks.

Relation Classification

PaperVenueDateCode
Enhancing Software-Related Information Extraction via Single-Choice Question Answering with Large Language ModelsOthers2024-04
CRE-LLM: A Domain-Specific Chinese Relation Extraction Framework with Fine-tuned Large Language ModelArxiv2024-04GitHub
Recall, Retrieve and Reason: Towards Better In-Context Relation ExtractionIJCAI2024-04
Empirical Analysis of Dialogue Relation Extraction with Large Language ModelsIJCAI2024-04
Meta In-Context Learning Makes Large Language Models Better Zero and Few-Shot Relation ExtractorsIJCAI2024-04
Retrieval-Augmented Generation-based Relation ExtractionArxiv2024-04GitHub
Relation Extraction Using Large Language Models: A Case Study on Acupuncture Point LocationsArxiv2024-04
STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language ModelsAAAI2024-03
Grasping the Essentials: Tailoring Large Language Models for Zero-Shot Relation ExtractionArxiv2024-02
Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation ExtractionEMNLP Findings2023-12
GPT-RE: In-context Learning for Relation Extraction using Large Language ModelsEMNLP2023-12GitHub
Guideline Learning for In-context Information ExtractionEMNLP2023-12
Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!EMNLP Findings2023-12GitHub
LLMaAA: Making Large Language Models as Active AnnotatorsEMNLP Findings2023-12GitHub
Improving Unsupervised Relation Extraction by Augmenting Diverse Sentence PairsEMNLP2023-12GitHub
Revisiting Large Language Models as Zero-shot Relation ExtractorsEMNLP Findings2023-12
Mastering the Task of Open Information Extraction with Large Language Models and Consistent Reasoning EnvironmentArxiv2023-10
Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation ExtractorsACL Findings2023-07GitHub
How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?ACL Workshop2023-07GitHub
Sequence generation with label augmentation for relation extractionAAAI2023-06GitHub
Does Synthetic Data Generation of LLMs Help Clinical Text Mining?Arxiv2023-04
DORE: Document Ordered Relation Extraction based on Generative FrameworkEMNLP Findings2022-12
REBEL: Relation Extraction By End-to-end Language generationEMNLP Findings2021-11GitHub

Relation Triplet

Relation Strict

Event Extraction

Models targeting only EE tasks.

Event Detection

Event Argument Extraction

Event Detection & Argument Extraction

Universal Information Extraction

Unified models targeting multiple IE tasks.

NL-LLMs based

Code-LLMs based

Information Extraction Techniques

A taxonomy by techniques.

Supervised Fine-tuning

PaperVenueDateCode
Rethinking Negative Instances for Generative Named Entity RecognitionACL Findings2024GitHub
Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument ExtractionACL Findings2024GitHub
AutoRE: Document-Level Relation Extraction with Large Language ModelsACL Demos2024GitHub
Recall, Retrieve and Reason: Towards Better In-Context Relation ExtractionIJCAI2024-04
Empirical Analysis of Dialogue Relation Extraction with Large Language ModelsIJCAI2024-04
An Autoregressive Text-to-Graph Framework for Joint Entity and Relation ExtractionAAAI2024GitHub
Improving Recall of Large Language Models: A Model Collaboration Approach for Relational Triple ExtractionCOLING2024GitHub
ToNER: Type-oriented Named Entity Recognition with Generative Language ModelCOLING2024
CHisIEC: An Information Extraction Corpus for Ancient Chinese HistoryCOLING2024GitHub
KeyEE: Enhancing Low-Resource Generative Event Extraction with Auxiliary Keyword Sub-PromptOthers2024-04GitHub
VANER: Leveraging Large Language Model for Versatile and Adaptive Biomedical Named Entity RecognitionArxiv2024-04GitHub
LLMs in Biomedicine: A study on clinical Named Entity RecognitionArxiv2024-04
Mining experimental data from Materials Science literature with Large Language Models: an evaluation studyArxiv2024-04GitHub
CRE-LLM: A Domain-Specific Chinese Relation Extraction Framework with Fine-tuned Large Language ModelArxiv2024-04GitHub
Relation Extraction Using Large Language Models: A Case Study on Acupuncture Point LocationsArxiv2024-04
Improving Event Definition Following For Zero-Shot Event DetectionArxiv2024-03
Embedded Named Entity Recognition using Probing ClassifiersArxiv2024-03GitHub
EventRL: Enhancing Event Extraction with Outcome Supervision for Large Language ModelsArxiv2024-02
Structured information extraction from scientific text with large language modelsNature Communications2024-02GitHub
PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity RecognitionArxiv2024-02
UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity RecognitionICLR2024GitHub
GoLLIE: Annotation Guidelines improve Zero-Shot Information-ExtractionICLR2024GitHub
Set Learning for Generative Information ExtractionEMNLP2023-12
Efficient Data Learning for Open Information Extraction with Pre-trained Language ModelsEMNLP Findings2023-12
DemoSG: Demonstration-enhanced Schema-guided Generation for Low-resource Event ExtractionEMNLP Findings2023-12GitHub
Calibrated Seq2seq Models for Efficient and Generalizable Ultra-fine Entity TypingEMNLP Findings2023-12
GIELLM: Japanese General Information Extraction Large Language Model Utilizing Mutual Reinforcement EffectArxiv2023-11
GLiNER: Generalist Model for Named Entity Recognition using Bidirectional TransformerArxiv2023-11GitHub
Context-Aware Prompt for Generation-based Event Argument Extraction with Diffusion ModelsCIKM2023-10
Contextualized Soft Prompts for Extraction of Event ArgumentsACL Findings2023-07
AMPERE: AMR-Aware Prefix for Generation-Based Event Argument Extraction ModelACL2023-07GitHub
Debiasing Generative Named Entity Recognition by Calibrating Sequence LikelihoodACL short2023-07
DICE: Data-Efficient Clinical Event Extraction with Generative ModelsACL2023-07GitHub
Event Extraction as Question Generation and AnsweringACL short2023-07GitHub
NAG-NER: a Unified Non-Autoregressive Generation Framework for Various NER TasksACL Industry2023-07
Sequence generation with label augmentation for relation extractionAAAI2023-06GitHub
Unified Named Entity Recognition as Multi-Label Sequence GenerationIJCNN2023-06
InstructUIE: Multi-task Instruction Tuning for Unified Information ExtractionArxiv2023-04GitHub
Structured information extraction from complex scientific text with fine-tuned large language modelsArxiv2022-12Demo
Generative Entity Typing with Curriculum LearningEMNLP2022-12GitHub
DORE: Document Ordered Relation Extraction based on Generative FrameworkEMNLP Findings2022-12
LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language ModelNeurIPS2022-10GitHub
LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable PromptingCOLING2022-10GitHub
GenIE: Generative Information ExtractionNAACL2022-07GitHub
DEGREE: A Data-Efficient Generative Event Extraction ModelNAACL2022-07GitHub
ClarET: Pre-training a correlation-aware context-to-event transformer for event-centric generation and classificationACL2022-05GitHub
DEEPSTRUCT: Pretraining of Language Models for Structure PredictionACL Findings2022-05GitHub
Dynamic prefix-tuning for generative template-based event extractionACL2022-05
Prompt for extraction? PAIE: prompting argument interaction for event argument extractionACL2022-05GitHub
Unified Structure Generation for Universal Information ExtractionACL2022-05GitHub
De-bias for generative extraction in unified NER taskACL2022-05
Document-level Entity-based Extraction as Template GenerationEMNLP2021-11GitHub
REBEL: Relation Extraction By End-to-end Language generationEMNLP Findings2021-11GitHub
A Unified Generative Framework for Various NER SubtasksACL2021-08GitHub
Template-Based Named Entity Recognition Using BARTACL Findings2021-08GitHub
Text2event: Controllable sequence-to- structure generation for end-to-end event extractionACL2021-08GitHub
Document-level event argument extraction by conditional generationNAACL2021-06GitHub
Structured prediction as translation between augmented natural languagesICLR2021-01GitHub

Few-shot

Few-shot Fine-tuning

In-Context Learning

PaperVenueDateCode
TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event ExtractionACL Findings2024GitHub
RT: a Retrieving and Chain-of-Thought framework for few-shot medical named entity recognitionOthers2024-05GitHub
P-ICL: Point In-Context Learning for Named Entity Recognition with Large Language ModelsArxiv2024-06GitHub
LTNER: Large Language Model Tagging for Named Entity Recognition with Contextualized Entity MarkingArxiv2024-04GitHub
Enhancing Software-Related Information Extraction via Single-Choice Question Answering with Large Language ModelsOthers2024-04
LLMs in Biomedicine: A study on clinical Named Entity RecognitionArxiv2024-04
Out of Sesame Street: A Study of Portuguese Legal Named Entity Recognition Through In-Context LearningResearchGate2024-04
Mining experimental data from Materials Science literature with Large Language Models: an evaluation studyArxiv2024-04GitHub
Empirical Analysis of Dialogue Relation Extraction with Large Language ModelsIJCAI2024-04
Self-Improving for Zero-Shot Named Entity Recognition with Large Language ModelsNAACL Short2024GitHub
ConsistNER: Towards Instructive NER Demonstrations for LLMs with the Consistency of Ontology and ContextAAAI2024
On-the-fly Definition Augmentation of LLMs for Biomedical NERNAACL2024GitHub
CHisIEC: An Information Extraction Corpus for Ancient Chinese HistoryCOLING2024GitHub
Unlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple ExtractionCOLING2024
CodeKGC: Code Language Model for Generative Knowledge Graph ConstructionACM TALLIP2024-03GitHub
Document-Level In-Context Few-Shot Relation Extraction via Pre-Trained Language ModelsArxiv2024-02GitHub
In-Context Learning for Few-Shot Nested Named Entity RecognitionArxiv2024-02
Leveraging ChatGPT in Pharmacovigilance Event Extraction: An Empirical StudyEACL2024-02GitHub
Heuristic-Driven Link-of-Analogy Prompting: Enhancing Large Language Models for Document-Level Event Argument ExtractionArxiv2024-02
LinkNER: Linking Local Named Entity Recognition Models to Large Language Models using UncertaintyWWW2024
Small Language Model Is a Good Guide for Large Language Model in Chinese Entity Relation ExtractionArxiv2024-02
C-ICL: Contrastive In-context Learning for Information ExtractionArxiv2024-02
Improving Large Language Models for Clinical Named Entity Recognition via Prompt EngineeringArxiv2024-01GitHub
Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation ExtractionEMNLP Findings2023-12
GPT-RE: In-context Learning for Relation Extraction using Large Language ModelsEMNLP2023-12GitHub
Guideline Learning for In-context Information ExtractionEMNLP2023-12
Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!EMNLP Findings2023-12GitHub
Retrieval-Augmented Code Generation for Universal Information ExtractionArxiv2023-11
Mastering the Task of Open Information Extraction with Large Language Models and Consistent Reasoning EnvironmentArxiv2023-10
GPT-NER: Named Entity Recognition via Large Language ModelsArxiv2023-10GitHub
GPT Struct Me: Probing GPT Models on Narrative Entity ExtractionWI-IAT2023-10GitHub
Learning In-context Learning for Named Entity Recognition ACL2023-07GitHub
Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation ExtractorsACL Findings2023-07GitHub
Code4Struct: Code Generation for Few-Shot Event Structure PredictionACL2023-07GitHub
CODEIE: Large Code Generation Models are Better Few-Shot Information ExtractorsACL2023-07GitHub
How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?ACL Workshop2023-07GitHub
PromptNER : Prompting For Named Entity RecognitionArxiv2023-06GitHub
Unified Text Structuralization with Instruction-tuned Language ModelsArxiv2023-03

Zero-shot

Zero-shot Prompting

PaperVenueDateCode
ERA-CoT: Improving Chain-of-Thought through Entity Relationship AnalysisACL2024GitHub
Astronomical Knowledge Entity Extraction in Astrophysics Journal Articles via Large Language ModelsOthers2024-04
Mining experimental data from Materials Science literature with Large Language Models: an evaluation studyArxiv2024-04GitHub
Empirical Analysis of Dialogue Relation Extraction with Large Language ModelsIJCAI2024-04
Retrieval-Augmented Generation-based Relation ExtractionArxiv2024-04GitHub
Relation Extraction Using Large Language Models: A Case Study on Acupuncture Point LocationsArxiv2024-04
Meta In-Context Learning Makes Large Language Models Better Zero and Few-Shot Relation ExtractorsIJCAI2024-04
Self-Improving for Zero-Shot Named Entity Recognition with Large Language ModelsNAACL Short2024GitHub
CodeKGC: Code Language Model for Generative Knowledge Graph ConstructionACM TALLIP2024-03GitHub
On-the-fly Definition Augmentation of LLMs for Biomedical NERNAACL2024-03GitHub
Leveraging ChatGPT in Pharmacovigilance Event Extraction: An Empirical StudyEACL2024-02GitHub
A Simple but Effective Approach to Improve Structured Language Model Output for Information ExtractionArxiv2024-02
Small Language Model Is a Good Guide for Large Language Model in Chinese Entity Relation ExtractionArxiv2024-02
Improving Large Language Models for Clinical Named Entity Recognition via Prompt EngineeringArxiv2024-01GitHub
Improving Unsupervised Relation Extraction by Augmenting Diverse Sentence PairsEMNLP2023-12GitHub
Prompt-NER: Zero-shot Named Entity Recognition in Astronomy Literature via Large Language ModelsArxiv2023-10
Revisiting Large Language Models as Zero-shot Relation ExtractorsEMNLP Findings2023-10
Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation ExtractorsACL Findings2023-07GitHub
Code4Struct: Code Generation for Few-Shot Event Structure PredictionACL2023-07GitHub
A Monte Carlo Language Model Pipeline for Zero-Shot Sociopolitical Event ExtractionNeurIPS Workshop2023-10
Global Constraints with Prompting for Zero-Shot Event Argument ClassificationEACL Findings2023-05
Zero-Shot Information Extraction via Chatting with ChatGPTArxiv2023-02GitHub

Cross-Domain Learning

Cross-Type Learning

Data Augmentation

Data Annotation

Knowledge Retrieval

Inverse Generation

Synthetic Datasets for Instruction-tuning

Prompts Design

Question Answer

Chain of Thought

Self-Improvement

Constrained Decoding Generation

Specific Domain

PaperDomainVenueDateCode
Granular Entity Mapper: Advancing Fine-grained Multimodal Named Entity Recognition and GroundingMultimodalEMNLP Findings2024
LLMs as Bridges: Reformulating Grounded Multimodal Named Entity RecognitionMultimodalACL Findings2024GitHub
RT: a Retrieving and Chain-of-Thought framework for few-shot medical named entity recognitionMedicalOthers2024-05GitHub
Astro-NER -- Astronomy Named Entity Recognition: Is GPT a Good Domain Expert Annotator?AstronomyArxiv2024-05
Astronomical Knowledge Entity Extraction in Astrophysics Journal Articles via Large Language ModelsAstronomyOthers2024-04
VANER: Leveraging Large Language Model for Versatile and Adaptive Biomedical Named Entity RecognitionBiomedicalArxiv2024-04GitHub
LLMs in Biomedicine: A study on clinical Named Entity RecognitionBiomedicalArxiv2024-04
Enhancing Software-Related Information Extraction via Single-Choice Question Answering with Large Language ModelsSoftwareOthers2024-04
Out of Sesame Street: A Study of Portuguese Legal Named Entity Recognition Through In-Context LearningLegalResearchGate2024-04
Mining experimental data from Materials Science literature with Large Language Models: an evaluation studyScientificArxiv2024-04GitHub
Relation Extraction Using Large Language Models: A Case Study on Acupuncture Point LocationsAcupuncture PointArxiv2024-04
Advancing Entity Recognition in Biomedicine via Instruction Tuning of Large Language ModelsBiomedicalBioinformatics2024-03GitHub
Distilling Named Entity Recognition Models for Endangered Species from Large Language ModelsEndangered SpeciesArxiv2024-03
CHisIEC: An Information Extraction Corpus for Ancient Chinese HistoryHistoricalCOLING2024-03GitHub
On-the-fly Definition Augmentation of LLMs for Biomedical NERBiomedicalNAACL2024-03GitHub
Improving LLM-Based Health Information Extraction with In-Context LearningHealthOthers2024-03
Structured information extraction from scientific text with large language modelsScientificNat. Commun.2024-02GitHub
Leveraging ChatGPT in Pharmacovigilance Event Extraction: An Empirical StudyPharmacovigilanceEACL2024-02GitHub
Structured information extraction from scientific text with large language modelsScientificNat. Commun.2024-02GitHub
Combining prompt‑based language models and weak supervision for labeling named entity recognition on legal documentsLegalOthers2024-02
Improving Large Language Models for Clinical Named Entity Recognition via Prompt EngineeringClinicalArxiv2024-01GitHub
Impact of Sample Selection on In-Context Learning for Entity Extraction from Scientific WritingScientificEMNLP Findings2023-12GitHub
Prompting ChatGPT in MNER: Enhanced Multimodal Named Entity Recognition with Auxiliary Refined KnowledgeMultimodalENMLP Findings2023-12GitHub
In-context Learning for Few-shot Multimodal Named Entity RecognitionMultimodalENMLP Findings2023-12
PolyIE: A Dataset of Information Extraction from Polymer Material Scientific LiteraturePolymer MaterialArxiv2023-11GitHub
Prompt-NER: Zero-shot Named Entity Recognition in Astronomy Literature via Large Language ModelsAstronomicalArxiv2023-10
Inspire the Large Language Model by External Knowledge on BioMedical Named Entity RecognitionBiomedicalArxiv2023-09
Chain-of-Thought Prompt Distillation for Multimodal Named Entity Recognition and Multimodal Relation ExtractionMultimodalArxiv2023-08
DICE: Data-Efficient Clinical Event Extraction with Generative ModelsClinicalACL2023-07GitHub
How far is Language Model from 100% Few-shot Named Entity Recognition in Medical DomainMedicalArxiv2023-07GitHub
Large Language Models as Instructors: A Study on Multilingual Clinical Entity ExtractionMultilingual / ClinicalBioNLP2023-07GitHub
Does Synthetic Data Generation of LLMs Help Clinical Text Mining?ClinicalArxiv2023-04
Yes but.. Can ChatGPT Identify Entities in Historical DocumentsHistoricalJCDL2023-03
Zero-shot Clinical Entity Recognition using ChatGPTClinicalArxiv2023-03
Structured information extraction from complex scientific text with fine-tuned large language modelsScientificArxiv2022-12Demo
Multilingual generative language models for zero-shot cross-lingual event argument extractionMultilingualACL2022-05GitHub

Evaluation and Analysis

PaperVenueDateCode
TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event ExtractionACL Findings2024GitHub
IEPile: Unearthing Large-Scale Schema-Based Information Extraction CorpusACL Short2024GitHub
CHisIEC: An Information Extraction Corpus for Ancient Chinese HistoryCOLING2024GitHub
GenRES: Rethinking Evaluation for Generative Relation Extraction in the Era of Large Language ModelsNAACL2024GitHub
Empirical Analysis of Dialogue Relation Extraction with Large Language ModelsIJCAI2024
Astro-NER -- Astronomy Named Entity Recognition: Is GPT a Good Domain Expert Annotator?Arxiv2024-05
Relation Extraction Using Large Language Models: A Case Study on Acupuncture Point LocationsArxiv2024-04
Mining experimental data from Materials Science literature with Large Language Models: an evaluation studyArxiv2024-04GitHub
Distilling Named Entity Recognition Models for Endangered Species from Large Language ModelsArxiv2024-03
LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future OpportunitiesArxiv2024-02GitHub
Few shot clinical entity recognition in three languages: Masked language models outperform LLM promptingArxiv2024-02
Information Extraction from Legal Wills: How Well Does GPT-4 Do?EMNLP Findings2023-12GitHub
Information Extraction in Low-Resource Scenarios: Survey and PerspectiveArxiv2023-12GitHub
Empirical Study of Zero-Shot NER with ChatGPTEMNLP2023-12GitHub
NERetrieve: Dataset for Next Generation Named Entity Recognition and RetrievalEMNLP Findings2023-12GitHub
Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information ExtractionEMNLP2023-12GitHub
PolyIE: A Dataset of Information Extraction from Polymer Material Scientific LiteratureArxiv2023-11GitHub
XNLP: An Interactive Demonstration System for Universal Structured NLPArxiv2023-08Demo
A Zero-shot and Few-shot Study of Instruction-Finetuned Large Language Models Applied to Clinical and Biomedical TasksArxiv2023-07
How far is Language Model from 100% Few-shot Named Entity Recognition in Medical DomainArxiv2023-07GitHub
Revisiting Relation Extraction in the era of Large Language ModelsACL2023-07GitHub
Zero-shot Temporal Relation Extraction with ChatGPTBioNLP2023-07
InstructIE: A Chinese Instruction-based Information Extraction DatasetArxiv2023-05GitHub
Is Information Extraction Solved by ChatGPT? An Analysis of Performance, Evaluation Criteria, Robustness and ErrorsArxiv2023-05GitHub
Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and FaithfulnessArxiv2023-04GitHub
Exploring the Feasibility of ChatGPT for Event ExtractionArxiv2023-03
Yes but.. Can ChatGPT Identify Entities in Historical DocumentsJCDL2023-03
Zero-shot Clinical Entity Recognition using ChatGPTArxiv2023-03
Thinking about GPT-3 In-Context Learning for Biomedical IE? Think AgainEMNLP Findings2022-12GitHub
Large Language Models are Few-Shot Clinical Information ExtractorsEMNLP2022-12Huggingface

Project and Toolkit

Recently Updated Papers

2024/09/04

PaperVenueDateCode
Timeline-based Sentence Decomposition with In-Context Learning for Temporal Fact ExtractionACL2024-08GitHub
Epidemic Information Extraction for Event-Based Surveillance using Large Language ModelsICICT2024-08
SpeechEE: A Novel Benchmark for Speech Event ExtractionACM MM2024-08GitHub
HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information ExtractionArxiv2024-08
Knowledge AI: Fine-tuning NLP Models for Facilitating Scientific Knowledge Extraction and UnderstandingArxiv2024-08
Target Prompting for Information Extraction with Vision Language ModelArxiv2024-08
Evaluating Named Entity Recognition Using Few-Shot Prompting with Large Language ModelsArxiv2024-08GitHub
Utilizing Large Language Models for Named Entity Recognition in Traditional Chinese Medicine against COVID-19 Literature: Comparative StudyArxiv2024-08
CLLMFS: A Contrastive Learning enhanced Large Language Model Framework for Few-Shot Named Entity RecognitionECAI2024-08
LLMs are not Zero-Shot Reasoners for Biomedical Information ExtractionArxiv2024-08
Label Alignment and Reassignment with Generalist Large Language Model for Enhanced Cross-Domain Named Entity RecognitionArxiv2024-07
MMM: Multilingual Mutual Reinforcement Effect Mix Datasets & Test with Open-domain Information Extraction Large Language ModelsArxiv2024-08GitHub
FsPONER: Few-shot Prompt Optimization for Named Entity Recognition in Domain-specific ScenariosECAI2024-07GitHub
Adapting Multilingual LLMs to Low-Resource Languages with Knowledge Graphs via AdaptersKaLLM workshop2024-07GitHub
Show Less, Instruct More: Enriching Prompts with Definitions and Guidelines for Zero-Shot NERArxiv2024-07
Large Language Models Struggle in Token-Level Clinical Named Entity RecognitionAMIA2024-08
GLiNER multi-task: Generalist Lightweight Model for Various Information Extraction TasksArxiv2024-08
Retrieval Augmented Instruction Tuning for Open NER with Large Language ModelsArxiv2024-06GitHub
Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity RecognitionArxiv2024-06GitHub
Fighting Against the Repetitive Training and Sample Dependency Problem in Few-shot Named Entity RecognitionIEEE Access2024-06GitHub
llmNER: (Zero|Few)-Shot Named Entity Recognition, Exploiting the Power of Large Language ModelsArxiv2024-06GitHub
Assessing the Performance of Chinese Open Source Large Language Models in Information Extraction TasksArxiv2024-06

Datasets

* denotes the dataset is multimodal. # refers to the number of categories or sentences.

TaskDatasetDomain#Class#Train#Val#TestLink
NERACE04News76202745812Link
ACE05News772999711060Link
BC5CDRBiomedical2456045814797Link
Broad Twitter CorpusSocial Media3633810012000Link
CADECBiomedical1534010971160Link
CoNLL03News41404132503453Link
CoNLLppNews41404132503453Link
CrossNER-AIArtificial Intelligence14100350431Link
CrossNER-LiteratureLiterary12100400416
CrossNER-MusicMusical13100380465
CrossNER-PoliticsPolitical9199540650
CrossNER-ScienceScientific17200450543
FabNERScientific12943521822064Link
Few-NERDGeneral661317671882437468Link
FindVehicleTraffic21215652077720777Link
GENIABiomedical51502316691854Link
HarveyNERSocial Media4396713011303Link
MIT-MovieSocial Media12977424422442Link
MIT-RestaurantSocial Media8765915201520Link
MultiNERDWikipedia161341441000010000Link
NCBIBiomedical45432923940Link
OntoNotes 5.0General185992485288262Link
ShARe13Biomedical18508120509009Link
ShARe14Biomedical117404136015850Link
SNAP*Social Media4429014321459Link
Temporal Twitter Corpus (TTC)Social Meida3100005001500Link
Tweebank-NERSocial Media416397101201Link
Twitter2015*Social Media4400010003357Link
Twitter2017*Social Media43373723723Link
TwitterNER7Social Media77111886576Link
WikiDiverse*News136312755757Link
WNUT2017Social Media6339410091287Link
REACE05News71005124202050Link
ADEBiomedical13417427428Link
CoNLL04News5922231288Link
DocREDWikipedia963008300700Link
MNRE*Social Media231224716241614Link
NYTNews245619650005000Link
Re-TACREDNews40584651958413418Link
SciERCScientific71366187397Link
SemEval2010General19650714932717Link
TACREDNews42681242263115509Link
TACREVNews42681242263115509Link
EEACE05News33/2217172923832Link
CASIECybersecurity5/261118917783208Link
GENIA11Biomedical9/11873010911092Link
GENIA13Biomedical13/74000500500Link
PHEEBiomedical2/162898961968Link
RAMSNews139/657329924871Link
WikiEventsWikipedia50/595262378492Link

Star History

Star History Chart

cross-domain-learning
data-augmentation
event-arguments
event-detection
event-extraction
few-shot-learning
in-context-learning
information-extraction
knowledge-graph-construction
large-language-models
named-entity-recognition
relation-extraction
zero-shot-learning

Significant stargazers

Donatas Remeika

19 followers · starred Apr 2024

Nilanjan De

33 followers · starred Jan 2024