2 results found Sort:

ictnlp
TruthX ictnlp
3
75
gpl-3.0
4
Code for ACL 2024 paper "TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space"
llm llms gpt-4 llama llama2 llama3 safety chatglm chatgpt mistral baichuan truthfulness hallucination llm-inference explainable-ai hallucinations language-model representation
Created 2024-02-27
18 commits to main branch, last one 3 months ago
OpenMOSS
Say-I-Dont-Know OpenMOSS
3
50
unknown
1
[ICML'2024] Can AI Assistants Know What They Don't Know?
alignment truthfulness large-language-models
Created 2024-01-18
9 commits to main branch, last one 4 months ago