Retriever-generator-verification: A novel approach to enhancing factual coherence in open-domain question answering

doi:10.1016/j.ipm.2025.104147

	Retriever-generator-verification: A novel approach to enhancing factual coherence in open-domain question answering
	Sun, Shiqi 2,3; Zhang, Kun 4; Li, Jingyuan 1; Yu, Min 5; Hou, Kun 1; Wang, Yuanzhuo 2; Cheng, Xueqi 2
	2025-07-01
发表期刊	INFORMATION PROCESSING & MANAGEMENT
ISSN	0306-4573
卷号	62 期号:4 页码:16
摘要	In recent research on open-domain question answering (ODQA), significant advances have been achieved by merging document retrieval techniques with large language models (LLMs) to answer questions. However, current ODQA methods present two challenges: the introduction of noise during retrieval and granularity errors during generation. To address these challenges, we propose the Retriever-Generator-Verification (RGV) framework, which consists of the Evidence Document Generator (EDG), the Candidate Entities Generator (CEG), and the Candidate Subgraphs Validator and Ranker (CSVR). EDG combines retrieval and generative mechanisms to construct comprehensive reference documents, ensuring broad coverage of potential answers. CEG then extracts and expands multi-dimensional candidate answer entities from these reference documents, capturing finer-grained information. Finally, CSVR verifies the candidate subgraphs against external knowledge sources and ranks them based on relevance, refining the final answers to enhance their accuracy and reliability. By systematically integrating these components, the RGV framework improves the completeness of retrieved information while effectively mitigating noise during retrieval and granularity errors during generation, thereby enhancing the overall reliability of ODQA. We assessed the efficacy of our method on three widely used datasets, and the experimental results demonstrate that our method exhibits competitive performance in benchmark tests. Compared to the state-of-the-art method, our approach achieves a 2.3% improvement in F1 score on the WebQSP dataset and a 1.3% increase in Hits@1 on the CWQ dataset.
关键词	Question answering Large language model Information retrieval In-context learning
DOI	10.1016/j.ipm.2025.104147
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62172393] ; Key Research and Development Project of Henan Province[241111211900] ; Zhongyuanyingcai Program-Funded to Central Plains Science and Technology Innovation Leading Talent Program[204200510002]
WOS研究方向	Computer Science ; Information Science & Library Science
WOS类目	Computer Science, Information Systems ; Information Science & Library Science
WOS记录号	WOS:001458884300001
出版者	ELSEVIER SCI LTD
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/40663
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Li, Jingyuan
作者单位	1.Beijing Technol & Business Univ, Sch Comp & Artificial Intelligence, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, CAS Key Lab AI Safety, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Beijing, Peoples R China 4.Tencent Inc, Pattern Recognit Ctr, WeChat AI, Beijing, Peoples R China 5.Chinese Acad Sci, Inst Informat Engn, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Sun, Shiqi,Zhang, Kun,Li, Jingyuan,et al. Retriever-generator-verification: A novel approach to enhancing factual coherence in open-domain question answering[J]. INFORMATION PROCESSING & MANAGEMENT,2025,62(4):16.
APA	Sun, Shiqi.,Zhang, Kun.,Li, Jingyuan.,Yu, Min.,Hou, Kun.,...&Cheng, Xueqi.(2025).Retriever-generator-verification: A novel approach to enhancing factual coherence in open-domain question answering.INFORMATION PROCESSING & MANAGEMENT,62(4),16.
MLA	Sun, Shiqi,et al."Retriever-generator-verification: A novel approach to enhancing factual coherence in open-domain question answering".INFORMATION PROCESSING & MANAGEMENT 62.4(2025):16.