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.
Anthology ID:
2024.findings-acl.499
Volume:
Findings of the Association for Computational Linguistics ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand and virtual meeting
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8424–8436
Language:
URL:
https://aclanthology.org/2024.findings-acl.499
DOI:
Bibkey:
Cite (ACL):
Ante Wang, Linfeng Song, Baolin Peng, Lifeng Jin, Ye Tian, Haitao Mi, Jinsong Su, and Dong Yu. 2024. Improving LLM Generations via Fine-Grained Self-Endorsement. In Findings of the Association for Computational Linguistics ACL 2024, pages 8424–8436, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
Cite (Informal):
Improving LLM Generations via Fine-Grained Self-Endorsement (Wang et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.findings-acl.499.pdf