TY - GEN
T1 - Mitigating Entity-Level Hallucination in Large Language Models
AU - Su, Weihang
AU - Tang, Yichen
AU - Ai, Qingyao
AU - Wang, Changyue
AU - Wu, Zhijing
AU - Liu, Yiqun
N1 - Publisher Copyright:
© 2024 Owner/Author.
PY - 2024/12/8
Y1 - 2024/12/8
N2 - 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.
AB - 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.
KW - Hallucination
KW - Large Language Model
KW - Retrieval Augmented Generation
UR - http://www.scopus.com/inward/record.url?scp=85215525059&partnerID=8YFLogxK
U2 - 10.1145/3673791.3698403
DO - 10.1145/3673791.3698403
M3 - Conference contribution
AN - SCOPUS:85215525059
T3 - SIGIR-AP 2024 - Proceedings of the 2024 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region
SP - 23
EP - 31
BT - SIGIR-AP 2024 - Proceedings of the 2024 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region
PB - Association for Computing Machinery, Inc
T2 - 2024 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region, SIGIR-AP 2024
Y2 - 9 December 2024 through 12 December 2024
ER -