Exécution de notre outil de synthèse sur un nouvel article

Vérifiez l’article ci-dessous, puis lancez sa synthèse.


Mitigating Entity-Level Hallucination in Large Language Models

Weihang Su (Tsinghua University), Yichen Tang (Tsinghua University), Qingyao Ai (Tsinghua University), Changyue Wang (Tsinghua University), Zhijing Wu (Beijing Institute of Technology), Yiqun Liu (Tsinghua University)

Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region (SIGIR-AP)
DOI: 10.1145/3673791.3698403 (Computer Science)
Licence : CC BY

Résumé : 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.

Publié le 08 Déc. 2024