Internal and External Knowledge Interactive Refinement Framework for Knowledge-Intensive Question Answering

ACL ARR 2024 December Submission2401 Authors

16 Dec 2024 (modified: 05 Feb 2025)ACL ARR 2024 December SubmissionEveryoneRevisionsBibTeXCC BY 4.0
Abstract: Recent works have attempted to integrate external knowledge into LLMs to address the limitations and potential factual errors in LLM-generated content. However, how to retrieve the correct knowledge from the large amount of external knowledge imposes a challenge. To this end, we empirically observe that LLMs have already encoded rich knowledge in their pretrained parameters and utilizing these internal knowledge improves the retrieval of external knowledge when applying them to knowledge-intensive tasks. In this paper, we propose a new internal and external knowledge interactive refinement paradigm dubbed IEKR to utilize internal knowledge in LLM to help retrieve relevant knowledge from the external knowledge base, as well as exploit the external knowledge to refine the hallucination of generated internal knowledge. By simply adding a prompt like “Tell me something about” to the LLMs, we try to review related explicit knowledge and insert them with the query into the retriever for external retrieval. The external knowledge is utilized to complement the internal knowledge into input of LLM for answers. We conduct experiments on 3 benchmark datasets in knowledge-intensive question answering task with different LLMs and domains, achieving the new state-of-the-art. Further analysis shows the effectiveness of different modules in our approach.
Paper Type: Long
Research Area: Question Answering
Research Area Keywords: Internal and External Knowledge, Interactive Refinement
Contribution Types: Model analysis & interpretability
Languages Studied: English
Submission Number: 2401
Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview