ArbGraph: Conflict-Aware Evidence Arbitration for Reliable Long-Form Retrieval-Augmented Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913047956684800 |
|---|---|
| author | Niu, Qingying Wang, Yuhao Ren, Ruiyang Fang, Bohui Zhao, Wayne Xin |
| author_facet | Niu, Qingying Wang, Yuhao Ren, Ruiyang Fang, Bohui Zhao, Wayne Xin |
| contents | Retrieval-augmented generation (RAG) remains unreliable in long-form settings, where retrieved evidence is noisy or contradictory, making it difficult for RAG pipelines to maintain factual consistency. Existing approaches focus on retrieval expansion or verification during generation, leaving conflict resolution entangled with generation. To address this limitation, we propose ArbGraph, a framework for pre-generation evidence arbitration in long-form RAG that explicitly resolves factual conflicts. ArbGraph decomposes retrieved documents into atomic claims and organizes them into a conflict-aware evidence graph with explicit support and contradiction relations. On top of this graph, we introduce an intensity-driven iterative arbitration mechanism that propagates credibility signals through evidence interactions, enabling the system to suppress unreliable and inconsistent claims before final generation. In this way, ArbGraph separates evidence validation from text generation and provides a coherent evidence foundation for downstream long-form generation. We evaluate ArbGraph on two widely used long-form RAG benchmarks, LongFact and RAGChecker, using multiple large language model backbones. Experimental results show that ArbGraph consistently improves factual recall and information density while reducing hallucinations and sensitivity to retrieval noise. Additional analyses show that these gains are evident under conflicting or ambiguous evidence, highlighting the effectiveness of evidence-level conflict resolution for improving the reliability of long-form RAG. The implementation is publicly available at https://github.com/1212Judy/ArbGraph. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_18362 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ArbGraph: Conflict-Aware Evidence Arbitration for Reliable Long-Form Retrieval-Augmented Generation Niu, Qingying Wang, Yuhao Ren, Ruiyang Fang, Bohui Zhao, Wayne Xin Computation and Language Information Retrieval Retrieval-augmented generation (RAG) remains unreliable in long-form settings, where retrieved evidence is noisy or contradictory, making it difficult for RAG pipelines to maintain factual consistency. Existing approaches focus on retrieval expansion or verification during generation, leaving conflict resolution entangled with generation. To address this limitation, we propose ArbGraph, a framework for pre-generation evidence arbitration in long-form RAG that explicitly resolves factual conflicts. ArbGraph decomposes retrieved documents into atomic claims and organizes them into a conflict-aware evidence graph with explicit support and contradiction relations. On top of this graph, we introduce an intensity-driven iterative arbitration mechanism that propagates credibility signals through evidence interactions, enabling the system to suppress unreliable and inconsistent claims before final generation. In this way, ArbGraph separates evidence validation from text generation and provides a coherent evidence foundation for downstream long-form generation. We evaluate ArbGraph on two widely used long-form RAG benchmarks, LongFact and RAGChecker, using multiple large language model backbones. Experimental results show that ArbGraph consistently improves factual recall and information density while reducing hallucinations and sensitivity to retrieval noise. Additional analyses show that these gains are evident under conflicting or ambiguous evidence, highlighting the effectiveness of evidence-level conflict resolution for improving the reliability of long-form RAG. The implementation is publicly available at https://github.com/1212Judy/ArbGraph. |
| title | ArbGraph: Conflict-Aware Evidence Arbitration for Reliable Long-Form Retrieval-Augmented Generation |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2604.18362 |