[2H4-GS-11] AI and Society:

[2H4-GS-11-02] Proposal for Correcting Sentence-Level Quotation Errors Generated by Large Language Models in Long-Context QA

〇Keita Kayaba¹, Yuji Yamaoka¹ (1. Fujitsu Limited)

Keywords:LLM, RAG, Evidence, Quotation Error Correction, Long-Context QA

The increasing adoption of Retrieval-Augmented Generation (RAG) for long-context question answering in organizations has heightened the demand for human verification of outputs from large language models (LLMs). To address this, researchers propose instructing LLMs to provide sentence-level quotations as evidence alongside their responses to facilitate the verification process. However, LLMs occasionally generate quotation errors, which complicate verification efforts. Our research introduces a novel method integrating automated correction processes with the self-correction capabilities of LLMs to address quotation errors. Our experiments demonstrate that the proposed method effectively corrects quotation errors and generates higher-quality quotations with fewer tokens than existing methods. This work highlights the utility of post-correction methods, like ours, for addressing sentence-level quotation errors generated by LLMs.