Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation

Xiaoying Zhang, Baolin Peng, Ye Tian, Jingyan Zhou, Lifeng Jin, Linfeng Song, Haitao Mi, Helen Meng


Abstract
Despite showing impressive abilities, large language models (LLMs) often struggle with factual inaccuracies, i.e., ”hallucinations”, even when they hold relevant knowledge. To mitigate these hallucinations, current approaches typically necessitate high-quality human factuality annotations. In this work, we explore Self-Alignment for Factuality, where we leverage the self-evaluation capability of an LLM to provide training signals that steer the model towards factuality. Specifically, we incorporate Self-Eval, a self-evaluation component, to prompt an LLM to validate the factuality of its own generated responses solely based on its internal knowledge. Additionally, we design Self-Knowledge Tuning (SK-Tuning) to augment the LLM’s self-evaluation ability by improving the model’s confidence estimation and calibration. We then utilize these self-annotated responses to fine-tune the model via Direct Preference Optimization algorithm. We show that the proposed self-alignment approach substantially enhances factual accuracy over Llama family models across three key knowledge-intensive tasks on TruthfulQA and BioGEN.
Anthology ID:
2024.acl-long.107
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:
1946–1965
Language:
URL:
https://aclanthology.org/2024.acl-long.107
DOI:
10.18653/v1/2024.acl-long.107
Bibkey:
Cite (ACL):
Xiaoying Zhang, Baolin Peng, Ye Tian, Jingyan Zhou, Lifeng Jin, Linfeng Song, Haitao Mi, and Helen Meng. 2024. Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1946–1965, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation (Zhang et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.107.pdf