Mitigating Entity-Level Hallucination in Large Language Models

Weihang Su, Yichen Tang, Qingyao Ai*, Changyue Wang, Zhijing Wu, Yiqun Liu

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

The emergence of Large Language Models (LLMs) has revolutionized how users access information, shifting from traditional search engines to direct question-and-answer interactions with LLMs. However, the widespread adoption of LLMs has revealed a significant challenge known as hallucination, wherein LLMs generate coherent yet factually inaccurate responses. This hallucination phenomenon has led to users' distrust in information retrieval systems based on LLMs. To tackle this challenge, this paper proposes Dynamic Retrieval Augmentation based on hallucination Detection (DRAD) as a novel method to detect and mitigate hallucinations in LLMs. DRAD improves upon traditional retrieval augmentation by dynamically adapting the retrieval process based on real-time hallucination detection. It features two main components: Real-time Hallucination Detection (RHD) for identifying potential hallucinations without external models, and Self-correction based on External Knowledge (SEK) for correcting these errors using external knowledge. Experiment results show that DRAD demonstrates superior performance in both detecting and mitigating hallucinations in LLMs. All of our code and data are open-sourced at https://github.com/oneal2000/EntityHallucination.

源语言英语
主期刊名SIGIR-AP 2024 - Proceedings of the 2024 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region
出版商Association for Computing Machinery, Inc
23-31
页数9
ISBN(电子版)9798400707247
DOI
出版状态已出版 - 8 12月 2024
活动2024 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region, SIGIR-AP 2024 - Tokyo, 日本
期限: 9 12月 202412 12月 2024

出版系列

姓名SIGIR-AP 2024 - Proceedings of the 2024 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region

会议

会议2024 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region, SIGIR-AP 2024
国家/地区日本
Tokyo
时期9/12/2412/12/24

指纹

探究 'Mitigating Entity-Level Hallucination in Large Language Models' 的科研主题。它们共同构成独一无二的指纹。

引用此

Su, W., Tang, Y., Ai, Q., Wang, C., Wu, Z., & Liu, Y. (2024). Mitigating Entity-Level Hallucination in Large Language Models. 在 SIGIR-AP 2024 - Proceedings of the 2024 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (页码 23-31). (SIGIR-AP 2024 - Proceedings of the 2024 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region). Association for Computing Machinery, Inc. https://doi.org/10.1145/3673791.3698403