Internal and External Knowledge Interactive Refinement Framework for Knowledge-Intensive Question Answering
Haowei Du, Dongyan Zhao

TL;DR
This paper introduces IEKR, a framework that enhances knowledge-intensive question answering by leveraging internal knowledge within LLMs to improve external knowledge retrieval and reduce hallucinations, achieving state-of-the-art results.
Contribution
The paper proposes a novel internal-external knowledge interactive refinement paradigm (IEKR) that effectively combines internal LLM knowledge with external retrieval for better answers.
Findings
Achieved state-of-the-art performance on three benchmark datasets.
Demonstrated the effectiveness of internal knowledge in improving external retrieval.
Showed that simple prompts can review internal knowledge to aid external knowledge retrieval.
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,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsIntelligent Tutoring Systems and Adaptive Learning
