arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.18362cs.CLcs.IR
收藏

ArbGraph:面向可靠长形式检索增强生成的冲突感知证据仲裁

ArbGraph: Conflict-Aware Evidence Arbitration for Reliable Long-Form Retrieval-Augmented Generation

Gaoling School of Artificial Intelligence(高岭人工智能学院);Renmin University of China(中国人民大学);Carnegie Mellon University(卡内基梅隆大学)

Qingying Niu, Yuhao Wang, Ruiyang Ren, Bohui Fang, Wayne Xin Zhao

AI总结:

ArbGraph通过预生成阶段的证据仲裁解决长形式RAG中的事实冲突,提升事实一致性与信息密度,减少幻觉和检索噪声影响。

摘要:

检索增强生成(RAG)在长形式场景中仍不可靠,因检索到的证据可能噪声或矛盾,使RAG流程难以维持事实一致性。现有方法侧重于生成阶段的检索扩展或验证,使冲突解决与生成交织。为解决此限制,我们提出ArbGraph,一种用于长形式RAG预生成阶段的证据仲裁框架,明确解决事实冲突。ArbGraph将检索文档分解为原子性声明,并组织成具有显式支持与矛盾关系的冲突感知证据图。在该图之上,我们引入一种强度驱动的迭代仲裁机制,通过证据交互传播可信度信号,使系统在最终生成前抑制不可靠且不一致的声明。这样,ArbGraph将证据验证与文本生成分离,并为下游长形式生成提供一致的证据基础。我们在两个广泛使用的长形式RAG基准LongFact和RAGChecker上评估ArbGraph,使用多个大语言模型基础架构。实验结果表明,ArbGraph在提升事实召回率和信息密度的同时,减少了幻觉和对检索噪声的敏感性。进一步分析显示,这些收益在存在冲突或模糊证据时尤为明显,突显了证据层面冲突解决对提升长形式RAG可靠性的有效性。实现已公开在https://github.com/1212Judy/ArbGraph。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑