Year: 2025
Type: conference-paper
Abstract: In this paper, we identify a critical problem, "lost-in-retrieval", in retrieval-augmented multihop question answering (QA): the key entities are missed in LLMs' sub-question decomposition."Lost-in-retrieval" significantly degrades the retrieval performance, which disrupts the reasoning chain and leads to the incorrect answers.To resolve this problem, we propose a progressive retrieval and rewriting method, namely ChainRAG, which sequentially handles each sub-question by completing missing key entities and retrieving relevant sentences from a sentence graph for answer generation.Each step in our retrieval and rewriting process builds upon the previous one, creating a seamless chain that leads to accurate retrieval and answers.Finally, all retrieved sentences and sub-question answers are integrated to generate a comprehensive answer to the original question.We evaluate ChainRAG on three multi-hop QA datasets-MuSiQue, 2Wiki, and HotpotQA-using three large language models: GPT4o-mini, Qwen2.5-72B, and GLM-4-Plus.Empirical results demonstrate that ChainRAG consistently outperforms baselines in both effectiveness and efficiency.
Authors: Rongzhi Zhu, Xiangyu Liu, Zequn Sun, Yiwei Wang, Wei Hu
Institutions: Nanjing University, University of California, Merced
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Award: G3137102087
OpenAlex ID: W4412944792