Improving LLM Generations via Fine-Grained Self-Endorsement
Ante Wang, Linfeng Song, Baolin Peng, Lifeng Jin, Ye Tian, Haitao Mi, Jinsong Su, Dong Yu
Abstract
This work studies mitigating fact-conflicting hallucinations for large language model (LLM) at inference time.Particularly, we propose a self-endorsement framework that leverages the fine-grained fact-level comparisons across multiple sampled responses.Compared with prior ensemble methods (e.g., self-consistency) that perform response-level selection, our approach can better alleviate hallucinations for knowledge-intensive tasks.Our approach can broadly benefit smaller and open-source LLMs as it mainly conducts simple content-based comparisons.Experiments on Biographies show that our method can effectively improve the factuality of generations with simple and intuitive prompts across different scales of LLMs.Besides, comprehensive analyses on TriviaQA and GSM8K demonstrate the potential of self-endorsement for broader application.
BibTeX
@inproceedings{wang-etal-2024-improving,
title = "Improving {LLM} Generations via Fine-Grained Self-Endorsement",
author = "Wang, Ante and
Song, Linfeng and
Peng, Baolin and
Jin, Lifeng and
Tian, Ye and
Mi, Haitao and
Su, Jinsong and
Yu, Dong",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.499/",
doi = "10.18653/v1/2024.findings-acl.499",
pages = "8424--8436"
}