Awesome-LLM-Controlled-Decoding-Generation

This repo aims to record advanced papers of controllable and decoding generation in LLMs.

We strongly encourage the researchers who want to promote their fantastic work in this area to make pull requests to update their paper's information!

Contents

• Review
• Papers
  • Decoding-time Alignment
  • Controlled Decoding
  • Tractable Probabilistic Models
  • Instruction Tuning
  • Non-autoregressive Language Model
  • NeuroLogic Decoding
  • Evaluation and Understanding
  • Application

---

Review & Survey

• Controllable Neural Text Generation
  Lilian Weng
  Lil'Log, 2021. [Link]

• A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models
  Hanqing Zhang, Haolin Song, Shaoyu Li, Ming Zhou, Dawei Song
  ACM Computing Surveys, 2023. [Paper]

• From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models
  Sean Welleck, Amanda Bertsch, Matthew Finlayson, Hailey Schoelkopf, Alex Xie, Graham Neubig, Ilia Kulikov, Zaid Harchaoui
  arXiv 2024. [Paper]

Benchmark

• Controllable Text Generation with Language Constraints
  Howard Chen, Huihan Li, Danqi Chen, Karthik Narasimhan
  arXiv 2022. [Paper] [Github]

Technical Report

• LLM Critics Help Catch LLM Bugs
  Nat McAleese, Rai Michael Pokorny, Juan Felipe Ceron Uribe, Evgenia Nitishinskaya, Maja Trebacz, Jan Leike
  Jun 28, 2024. OpenAI. [Paper] [Link]

Papers

Decoding-time Alignment

• Decoding-time Realignment of Language Models
  Tianlin Liu, Shangmin Guo, Leonardo Bianco, Daniele Calandriello, Quentin Berthet, Felipe Llinares, Jessica Hoffmann, Lucas Dixon, Michal Valko, Mathieu Blondel
  ICML 2024. [Paper]

• DeAL: Decoding-time Alignment for Large Language Models
  James Y. Huang, Sailik Sengupta, Daniele Bonadiman, Yi-an Lai, Arshit Gupta, Nikolaos Pappas, Saab Mansour, Katrin Kirchhoff, Dan Roth
  arXiv 2024. [Paper]

• Decoding-Time Language Model Alignment with Multiple Objectives
  Ruizhe Shi, Yifang Chen, Yushi Hu, Alisa Liu, Hannaneh Hajishirzi, Noah A. Smith, Simon Du
  arXiv 2024. [Paper] [Github]

• Cascade Reward Sampling for Efficient Decoding-Time Alignment
  Bolian Li, Yifan Wang, Ananth Grama, Ruqi Zhang
  arXiv 2024. [Paper] [Github]

• Reward Steering with Evolutionary Heuristics for Decoding-time Alignment
  Anonymous ACL submission
  arXiv 2024. [Paper]

• DOLA: DECODING BY CONTRASTING LAYERS IMPROVES FACTUALITY IN LARGE LANGUAGE MODELS
  Yung-Sung Chuang, Yujia Xie, Hongyin Luo, Yoon Kim, James Glass, Pengcheng He
  ICLR 2024. [Paper] [Github]

• Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
  Kenneth Li, Oam Patel, Fernanda Viégas, Hanspeter Pfister, Martin Wattenberg
  NeurIPS 2023. [Paper] [Github]

• TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space
  Shaolei Zhang, Tian Yu, Yang Feng
  ACL 2024. [Paper] [Github]

• Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning
  Zhongzhi Chen, Xingwu Sun, Xianfeng Jiao, Fengzong Lian, Zhanhui Kang, Di Wang, Cheng-Zhong Xu
  AAAI 2024. [Paper] [Github]

• Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps
  Yung-Sung Chuang, Linlu Qiu, Cheng-Yu Hsieh, Ranjay Krishna, Yoon Kim, James Glass
  Arxiv 2024. [Paper] [Github]

• Trusting Your Evidence: Hallucinate Less with Context-aware Decoding
  Weijia Shi, Xiaochuang Han, Mike Lewis, Yulia Tsvetkov, Luke Zettlemoyer, Scott Wen-tau Yih
  NAACL 2024. [Paper] [Github]

• Mutual Information Alleviates Hallucinations in Abstractive Summarization
  Liam van der Poel, Ryan Cotterell, Clara Meister
  EMNLP 2022. [Paper] [Github]

• Locating and Editing Factual Associations in GPT
  Kevin Meng, David Bau, Alex Andonian, Yonatan Belinkov
  NeurIPS 2022. [Paper] [Website]

Controlled Decoding

• Aligning Large Language Models with Representation Editing: A Control Perspective
  Lingkai Kong, Haorui Wang, Wenhao Mu, Yuanqi Du, Yuchen Zhuang, Yifei Zhou, Yue Song, Rongzhi Zhang, Kai Wang, Chao Zhang
  Arxiv 2024. [Paper]

• PaCE: Parsimonious Concept Engineering for Large Language Models
  Jinqi Luo, Tianjiao Ding, Kwan Ho Ryan Chan, Darshan Thaker, Aditya Chattopadhyay, Chris Callison-Burch, René Vidal
  arXiv 2024. [Paper] [Github]

• Controlled Decoding from Language Models
  Sidharth Mudgal, Jong Lee, Harish Ganapathy, YaGuang Li, Tao Wang, Yanping Huang, Zhifeng Chen, Heng-Tze Cheng, Michael Collins, Trevor Strohman, Jilin Chen, Alex Beutel, Ahmad Beirami
  ICML 2024. [Paper]

• Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models
  Zhanhui Zhou, Zhixuan Liu, Jie Liu, Zhichen Dong, Chao Yang, Yu Qiao
  arXiv 2024 [Paper] [Github]

• BWArea Model: Learning World Model, Inverse Dynamics, and Policy for Controllable Language Generation
  Chengxing Jia, Pengyuan Wang, Ziniu Li, Yi-Chen Li, Zhilong Zhang, Nan Tang, Yang Yu
  Arxiv 2024. [Paper]

• COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability
  Xingang Guo, Fangxu Yu, Huan Zhang, Lianhui Qin, Bin Hu
  ICML 2024. [Paper] [Github]

• Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs
  Xun Liang, Hanyu Wang, Shichao Song, Mengting Hu, Xunzhi Wang, Zhiyu Li, Feiyu Xiong, Bo Tang
  ACL 2024. [Ppaer] [Github]

• Controlled Text Generation via Language Model Arithmetic
  Jasper Dekoninck, Marc Fischer, Luca Beurer-Kellner, Martin Vechev
  ICLR 2024. [Paper] [Github]

• Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation
  Luca Beurer-Kellner, Marc Fischer, Martin Vechev
  arXiv 2024. [Paper]

• Controllable Text Generation with Neurally-Decomposed Oracle
  Tao Meng, Sidi Lu, Nanyun Peng, Kai-Wei Chang
  NeurIPS 2022. [Paper] [Github]

• BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases
  Xin Liu, Muhammad Khalifa, Lu Wang
  ACL 2023. [Paper] [Github]

• Controllable Text Generation with Neurally-Decomposed Oracle
  Xin Liu, Muhammad Khalifa, Lu Wang
  NeurIPS 2022. [Paper] [Github]

• COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics
  Lianhui Qin, Sean Welleck, Daniel Khashabi, Yejin Choi
  NeurIPS 2022 [Paper] [Github]

• Gradient-Based Constrained Sampling from Language Models
  Sachin Kumar, Biswajit Paria, Yulia Tsvetkov
  EMNLP 2022. [Paper] [Github]

• FUDGE: Controlled Text Generation With Future Discriminators
  Kevin Yang, Dan Klein
  NAACL 2021 [Paper] [Github]

• A Distributional Approach to Controlled Text Generation
  Muhammad Khalifa, Hady Elsahar, Marc Dymetman
  ICLR 2021. [Paper] [Github]

• Plug and Play Language Models: A Simple Approach to Controlled Text Generation
  Sumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, Piero Molino, Jason Yosinski, Rosanne Liu
  ICLR 2020 [Paper] [Github]

• Controlled Text Generation as Continuous Optimization with Multiple Constraints
  Sachin Kumar, Eric Malmi, Aliaksei Severyn, Yulia Tsvetkov
  NeurIPS 2020. [Paper] [Github]

Tractable Probabilistic Models

• Tractable Control for Autoregressive Language Generation
  Honghua Zhang, Meihua Dang, Nanyun Peng, Guy Van den Broeck
  ICML 2023 [Paper] [Github]

Multi-aspect Controllabled Text Generation

• An Extensible Plug-and-Play Method for Multi-Aspect Controllable Text Generation

• Xuancheng Huang, Zijun Liu, Peng Li, Tao Li, Maosong Sun, Yang Liu
  ACL 2023. [Paper] [Github]

• A Distributional Lens for Multi-Aspect Controllable Text Generation
  Yuxuan Gu, Xiaocheng Feng, Sicheng Ma, Lingyuan Zhang, Heng Gong, Bing Qin
  EMNLP 2022. [Paper] [Github]

Hallucination Mitigation

• Teaching Language Models to Hallucinate Less with Synthetic Tasks
  Erik Jones, Hamid Palangi, Clarisse Simões, Varun Chandrasekaran, Subhabrata Mukherjee, Arindam Mitra, Ahmed Awadallah, Ece Kamar
  ICLR 2024. [Paper]

• Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models
  Yuji Zhang, Sha Li, Jiateng Liu, Pengfei Yu, Yi R. Fung, Jing Li, Manling Li, Heng Ji
  arXiv 2024. [Paper]

Reinforcement Learning

• Critic-Guided Decoding for Controlled Text Generation
  Minbeom Kim, Hwanhee Lee, Kang Min Yoo, Joonsuk Park, Hwaran Lee, Kyomin Jung
  ACL 2023. [Paper] [Github]

Instruction Tuning

• COLLIE: Systematic Construction of Constrained Text Generation Tasks
  Shunyu Yao, Howard Chen, Austin W. Hanjie, Runzhe Yang, Karthik Narasimhan
  ICLR 2024. [Paper] [Github]

• Controlled Text Generation with Natural Language Instructions
  Wangchunshu Zhou, Yuchen Eleanor Jiang, Ethan Wilcox, Ryan Cotterell, Mrinmaya Sachan
  ICML 2023. [Paper] [Github]

• Toward Unified Controllable Text Generation via Regular Expression Instruction
  Xin Zheng, Hongyu Lin, Xianpei Han, Le Sun
  IJCNLP-AACL 2023. [Paper] [Github]

Non-autoregressive Language Model

• Xiang Lisa Li, John Thickstun, Ishaan Gulrajani, Percy Liang, Tatsunori B. Hashimoto
  Diffusion-LM Improves Controllable Text Generation
  NeurIPS 2022. [Paper] [Github]

NeuroLogic Decoding

• NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge
  Phillip Howard, Junlin Wang, Vasudev Lal, Gadi Singer, Yejin Choi, Swabha Swayamdipta
  NACCL 2024. [Paper] [Github]

• NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints
  Ximing Lu, Peter West, Rowan Zellers, Ronan Le Bras, Chandra Bhagavatula, Yejin Choi
  NAACL 2021. [Paper] [Github]

Evaluation and Understanding

• "We Need Structured Output": Towards User-centered Constraints on Large Language Model Output
  Michael Xieyang Liu, Frederick Liu, Alexander J. Fiannaca, Terry Koo, Lucas Dixon, Michael Terry, Carrie J. Cai
  CHI EA 2024. [Paper]

• Evaluating, Understanding, and Improving Constrained Text Generation for Large Language Models
  Xiang Chen, Xiaojun Wan
  Arxiv 2023. [Paper]

• Evaluating Large Language Models on Controlled Generation Tasks
  Jiao Sun, Yufei Tian, Wangchunshu Zhou, Nan Xu, Qian Hu, Rahul Gupta, John Frederick Wieting, Nanyun Peng, Xuezhe Ma
  EMNLP 2023. [Paper] [Github]

Application

• JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models
  Jillian Fisher, Ximing Lu, Jaehun Jung, Liwei Jiang, Zaid Harchaoui, Yejin Choi
  NAACL 2024. [Paper] [Github]

• Semantically-Aware Constrained Decoding for Code Generation
  Kristian Muñiz
  March 2024. [Link]

• Discrete Prompt Optimization via Constrained Generation for Zero-shot Re-ranker
  Sukmin Cho, Soyeong Jeong, Jeongyeon Seo, Jong C. Park
  ACL 2023. [Paper] [Github]

• Synchromesh: Reliable code generation from pre-trained language models
  Gabriel Poesia, Oleksandr Polozov, Vu Le, Ashish Tiwari, Gustavo Soares, Christopher Meek, Sumit Gulwani
  ICLR 2022. [Paper] [Github]