Shadowgraph
TrendingAbout
Sign in

HillZhang/untruthful_baichuan2_7b

Model

Untruthful-Baichuan2-7B

0

2 commits

3 linked in READMEs

updated Dec 21, 2023

See the code

README

Untruthful-Baichuan2-7B

We induce hallucinations from the original Baichuan2-7B by finetuning it on selected samples from HaluEval. We then use it in our ICD method for improve factuality of LLMs and evaluate the effectiveness on TruthfulQA. More details are provided in our Github and Paper.

baichuan
custom_code
English
feature-extraction
pytorch
text-generation-inference
transformers

Contributors

HillZhang

2 commits

Similar repos

HillZhang/untruthful_llama2_7b

Model

Untruthful-Llama2-7B

2

HillZhang/untruthful_mistral_7b

Model

Untruthful-Mistral-7B-v0.1

0

HillZhang/untruthful_llama2_7b_bio

Model

Untruthful-Llama2-7B-Bio

0

ICTNLP/Llama-2-7b-chat-TruthX

Model

TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space

6

HillZhang1999/ICD

Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced…

71

ICTNLP/TruthX

Model

TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space

5

likenneth/honest_llama2_chat_7B

Model

Ever wondering a less hallucinating LLaMA-2? Using the inference-time intervention (ITI) discussed…

9

ictnlp/TruthX

Code for ACL 2024 paper "TruthX: Alleviating Hallucinations by Editing Large Language Models in…

145

Linked in READMEs

sylinrl/TruthfulQA

TruthfulQA: Measuring How Models Imitate Human Falsehoods

947

README badge

RUCAIBox/HaluEval

This is the repository of HaluEval, a large-scale hallucination evaluation benchmark for Large…

598

README badge

HillZhang1999/ICD

Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced…

71

README badge

HillZhang/untruthful_baichuan2_7b

Model

Untruthful-Baichuan2-7B

0

2 commits

3 linked in READMEs

updated Dec 21, 2023

See the code

README

Untruthful-Baichuan2-7B

We induce hallucinations from the original Baichuan2-7B by finetuning it on selected samples from HaluEval. We then use it in our ICD method for improve factuality of LLMs and evaluate the effectiveness on TruthfulQA. More details are provided in our Github and Paper.

baichuan
custom_code
English
feature-extraction
pytorch
text-generation-inference
transformers

Similar repos

HillZhang/untruthful_llama2_7b

Model

Untruthful-Llama2-7B

2

HillZhang/untruthful_mistral_7b

Model

Untruthful-Mistral-7B-v0.1

0

HillZhang/untruthful_llama2_7b_bio

Model

Untruthful-Llama2-7B-Bio

0

ICTNLP/Llama-2-7b-chat-TruthX

Model

TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space

6

HillZhang1999/ICD

Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced…

71

ICTNLP/TruthX

Model

TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space

5

likenneth/honest_llama2_chat_7B

Model

Ever wondering a less hallucinating LLaMA-2? Using the inference-time intervention (ITI) discussed…

9

ictnlp/TruthX

Code for ACL 2024 paper "TruthX: Alleviating Hallucinations by Editing Large Language Models in…

145

Linked in READMEs

sylinrl/TruthfulQA

TruthfulQA: Measuring How Models Imitate Human Falsehoods

947

README badge

RUCAIBox/HaluEval

This is the repository of HaluEval, a large-scale hallucination evaluation benchmark for Large…

598

README badge

HillZhang1999/ICD

Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced…

71

README badge

Contributors

HillZhang

2 commits