ConRAG: Consensus-Driven Multi-View Retrieval for Multi-Hop Question Answering
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911723694325760 |
|---|---|
| author | Zhu, Yikai Chen, Kunfeng Zhong, Qihuang Liu, Juhua Du, Bo |
| author_facet | Zhu, Yikai Chen, Kunfeng Zhong, Qihuang Liu, Juhua Du, Bo |
| contents | Retrieval-augmented generation (RAG) has emerged as a promising paradigm for enhancing large language models (LLMs) on multi-hop question answering (QA), which requires reasoning over evidence from multiple documents. Current multi-hop RAG methods generally focus on either query-side task decomposition or corpus-side knowledge graph construction. Despite their progress, these methods still struggle to achieve satisfactory performance on complex multi-hop QA tasks. To this end, we propose ConRAG, a consensus-driven multi-view RAG framework that effectively boosts LLMs on complex multi-hop QA. The core of ConRAG is to systematically optimize both the query and corpus sides and to leverage multi-view evidence (relation, entity, and text signals) for more accurate retrieval. Extensive experiments on three multi-hop QA benchmarks show that ConRAG consistently outperforms all baselines by a clear margin, e.g., up to +26.9% average performance gains over vanilla RAG, and enables Gemma-4-31B to achieve a new state-of-the-art record on the challenging MuSiQue benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_28093 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ConRAG: Consensus-Driven Multi-View Retrieval for Multi-Hop Question Answering Zhu, Yikai Chen, Kunfeng Zhong, Qihuang Liu, Juhua Du, Bo Computation and Language Retrieval-augmented generation (RAG) has emerged as a promising paradigm for enhancing large language models (LLMs) on multi-hop question answering (QA), which requires reasoning over evidence from multiple documents. Current multi-hop RAG methods generally focus on either query-side task decomposition or corpus-side knowledge graph construction. Despite their progress, these methods still struggle to achieve satisfactory performance on complex multi-hop QA tasks. To this end, we propose ConRAG, a consensus-driven multi-view RAG framework that effectively boosts LLMs on complex multi-hop QA. The core of ConRAG is to systematically optimize both the query and corpus sides and to leverage multi-view evidence (relation, entity, and text signals) for more accurate retrieval. Extensive experiments on three multi-hop QA benchmarks show that ConRAG consistently outperforms all baselines by a clear margin, e.g., up to +26.9% average performance gains over vanilla RAG, and enables Gemma-4-31B to achieve a new state-of-the-art record on the challenging MuSiQue benchmark. |
| title | ConRAG: Consensus-Driven Multi-View Retrieval for Multi-Hop Question Answering |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2605.28093 |