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

Shaolei Zhang, Tian Yu, Yang Feng


Abstract
Large Language Models (LLMs) sometimes suffer from producing hallucinations, especially LLMs may generate untruthful responses despite knowing the correct knowledge. Activating the truthfulness within LLM is the key to fully unlocking LLM’s knowledge potential. In this paper, we propose TruthX, an inference-time intervention method to activate the truthfulness of LLM by identifying and editing the features within LLM’s internal representations that govern the truthfulness. TruthX employs an auto-encoder to map LLM’s representations into semantic and truthful latent spaces respectively, and applies contrastive learning to identify a truthful editing direction within the truthful space. During inference, by editing LLM’s internal representations in truthful space, TruthX effectively enhances the truthfulness of LLM. Experiments show that TruthX improves the truthfulness of 13 advanced LLMs by an average of 20% on TruthfulQA benchmark. Further analyses suggest that TruthX can control LLM to produce truthful or hallucinatory responses via editing only one vector in LLM’s internal representations.
Anthology ID:
2024.acl-long.483
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8908–8949
Language:
URL:
https://aclanthology.org/2024.acl-long.483
DOI:
10.18653/v1/2024.acl-long.483
Bibkey:
Cite (ACL):
Shaolei Zhang, Tian Yu, and Yang Feng. 2024. TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8908–8949, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space (Zhang et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.483.pdf