Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion

Xinping Zhao, Jindi Yu, Zhenyu Liu, Jifang Wang, Dongfang Li, Yibin Chen, Baotian Hu, Min Zhang


Abstract
As we all know, hallucinations prevail in Large Language Models (LLMs), where the generated content is coherent but factually incorrect, which inflicts a heavy blow on the widespread application of LLMs. Previous studies have shown that LLMs could confidently state non-existent facts rather than answering “I don’t know”. Therefore, it is necessary to resort to external knowledge to detect and correct the hallucinated content. Since manual detection and correction of factual errors is labor-intensive, developing an automatic end-to-end hallucination-checking approach is indeed a needful thing. To this end, we present Medico, a Multi-source evidence fusion enhanced hallucination detection and correction framework. It fuses diverse evidence from multiple sources, detects whether the generated content contains factual errors, provides the rationale behind the judgment, and iteratively revises the hallucinated content. Experimental results on evidence retrieval (0.964 HR@5, 0.908 MRR@5), hallucination detection (0.927-0.951 F1), and hallucination correction (0.973-0.979 approval rate) manifest the great potential of Medico. A video demo of Medico can be found at https://youtu.be/RtsO6CSesBI.
Anthology ID:
2024.emnlp-demo.4
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Delia Irazu Hernandez Farias, Tom Hope, Manling Li
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
34–45
Language:
URL:
https://aclanthology.org/2024.emnlp-demo.4
DOI:
Bibkey:
Cite (ACL):
Xinping Zhao, Jindi Yu, Zhenyu Liu, Jifang Wang, Dongfang Li, Yibin Chen, Baotian Hu, and Min Zhang. 2024. Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 34–45, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion (Zhao et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-demo.4.pdf