paper-with-me

홈 › Papers

Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering

2025-02-20 · Rongzhi Zhu, Xiangyu Liu, Zequn Sun, Yiwei Wang, Wei Hu

In this paper, we identify a critical problem, "lost-in-retrieval", in retrieval-augmented multi-hop 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$\unicode{x2013}$MuSiQue, 2Wiki, and HotpotQA$\unicode{x2013}$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.

📄 PDF Abstract BibTeX arXiv:2502.14245

Code (0)

등록된 구현이 없습니다.

Tasks

Answer GenerationMulti-hop Question AnsweringQuestion AnsweringRetrievalSentence

Similar Papers 제목 키워드 기반

Lost-in-the-Middle in Long-Text Generation: Synthetic Dataset, Evaluation Framework, and Mitigation

2025-03-10 · Junhao Zhang, Richong Zhang, Fanshuang Kong, Ziyang Miao 외

Existing long-text generation methods primarily concentrate on producing lengthy texts from short inputs, neglecting the long-input and long-output tasks. Such tasks have numerous practical applications while lacking ava…

Text Generation

A MapReduce Approach to Effectively Utilize Long Context Information in Retrieval Augmented Language Models

2024-12-17 · Gongbo Zhang, Zihan Xu, Qiao Jin, Fangyi Chen 외

While holding great promise for improving and facilitating healthcare, large language models (LLMs) struggle to produce up-to-date responses on evolving topics due to outdated knowledge or hallucination. Retrieval-augmen…

HallucinationRAGRetrievalRetrieval-augmented Generation

Removal of Hallucination on Hallucination: Debate-Augmented RAG

2025-05-24 · Wentao Hu, WengYu Zhang, Yiyang Jiang, Chen Jason Zhang 외

Retrieval-Augmented Generation (RAG) enhances factual accuracy by integrating external knowledge, yet it introduces a critical issue: erroneous or biased retrieval can mislead generation, compounding hallucinations, a ph…

HallucinationRAGRetrievalRetrieval-augmented Generation

DioR: Adaptive Cognitive Detection and Contextual Retrieval Optimization for Dynamic Retrieval-Augmented Generation

2025-04-14 · Hanghui Guo, Jia Zhu, Shimin Di, Weijie Shi 외

Dynamic Retrieval-augmented Generation (RAG) has shown great success in mitigating hallucinations in large language models (LLMs) during generation. However, existing dynamic RAG methods face significant limitations in t…

RAGRetrievalRetrieval-augmented Generation

MultiRAG: A Knowledge-guided Framework for Mitigating Hallucination in Multi-source Retrieval Augmented Generation

2025-08-05 · Wenlong Wu, Haofen Wang, Bohan Li, Peixuan Huang 외 arxiv

Retrieval Augmented Generation (RAG) has emerged as a promising solution to address hallucination issues in Large Language Models (LLMs). However, the integration of multiple retrieval sources, while potentially more inf…