SentGraph: Hierarchical Sentence Graph for Multi-hop Retrieval-Augmented Question Answering
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918519698882560 |
|---|---|
| author | Liang, Junli Zhou, Pengfei Zhou, Wangqiu Qing, Wenjie Zhao, Qi Wang, Ziwen Song, Qi Li, Xiangyang |
| author_facet | Liang, Junli Zhou, Pengfei Zhou, Wangqiu Qing, Wenjie Zhao, Qi Wang, Ziwen Song, Qi Li, Xiangyang |
| contents | Traditional Retrieval-Augmented Generation (RAG) effectively supports single-hop question answering with large language models but faces significant limitations in multi-hop question answering tasks, which require combining evidence from multiple documents. Existing chunk-based retrieval often provides irrelevant and logically incoherent context, leading to incomplete evidence chains and incorrect reasoning during answer generation. To address these challenges, we propose SentGraph, a sentence-level graph-based RAG framework that explicitly models fine-grained logical relationships between sentences for multi-hop question answering. Specifically, we construct a hierarchical sentence graph offline by first adapting Rhetorical Structure Theory to distinguish nucleus and satellite sentences, and then organizing them into topic-level subgraphs with cross-document entity bridges. During online retrieval, SentGraph performs graph-guided evidence selection and path expansion to retrieve fine-grained sentence-level evidence. Extensive experiments on four multi-hop question answering benchmarks demonstrate the effectiveness of SentGraph, validating the importance of explicitly modeling sentence-level logical dependencies for multi-hop reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_03014 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SentGraph: Hierarchical Sentence Graph for Multi-hop Retrieval-Augmented Question Answering Liang, Junli Zhou, Pengfei Zhou, Wangqiu Qing, Wenjie Zhao, Qi Wang, Ziwen Song, Qi Li, Xiangyang Computation and Language Artificial Intelligence Traditional Retrieval-Augmented Generation (RAG) effectively supports single-hop question answering with large language models but faces significant limitations in multi-hop question answering tasks, which require combining evidence from multiple documents. Existing chunk-based retrieval often provides irrelevant and logically incoherent context, leading to incomplete evidence chains and incorrect reasoning during answer generation. To address these challenges, we propose SentGraph, a sentence-level graph-based RAG framework that explicitly models fine-grained logical relationships between sentences for multi-hop question answering. Specifically, we construct a hierarchical sentence graph offline by first adapting Rhetorical Structure Theory to distinguish nucleus and satellite sentences, and then organizing them into topic-level subgraphs with cross-document entity bridges. During online retrieval, SentGraph performs graph-guided evidence selection and path expansion to retrieve fine-grained sentence-level evidence. Extensive experiments on four multi-hop question answering benchmarks demonstrate the effectiveness of SentGraph, validating the importance of explicitly modeling sentence-level logical dependencies for multi-hop reasoning. |
| title | SentGraph: Hierarchical Sentence Graph for Multi-hop Retrieval-Augmented Question Answering |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2601.03014 |