发表机构
School of Computing, Wichita State University; Department of Computer Science, American International University-Bangladesh（威奇托州立大学计算学院; 美国国际孟加拉大学计算机科学系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究多源检索增强生成中信息冲突问题，提出ERAG框架，通过将检索块转换为概率证据、用轻量级评估器和融合规则处理不确定性，实验表明该框架在标准问答有竞争力，在冲突情况下行为改善，是可信信息处理实用机制。
AI 中文摘要
检索增强生成将大语言模型建立在外部证据之上，但大多数流程仍将检索到的段落视为确定性且相互一致的上下文。在开放信息环境中，检索到的源可能因时间漂移、源错误、歧义或真正的不确定性而不一致。本文介绍了ERAG，一个不确定性感知的RAG框架，它在生成前将检索到的块转换为概率证据。一个轻量级评估器提取候选主张并将块级支持映射到狄利克雷证据。然后，一个保留冲突的邓普斯特-谢弗融合规则将未解决的分歧转化为认知不确定性，而不是将其归一化消除。生成器根据融合后的不确定性分数被路由到直接回答、冲突感知回答或弃权。在CRAG、ConflictQA和MuSiQue上的实验表明，ERAG在标准问答方面与最强的匹配基线保持竞争力，同时在冲突情况下改善了行为。在CRAG模糊子集上，幻觉从纠正性RAG的45.3%降至人工校准估计的34.8%，冲突解决从35.2%提高到51.2%，预期校准误差提高到0.122。这些结果表明，证据建模是基于基础模型的检索系统中进行可信信息处理的一种实用机制。
英文摘要
Retrieval-augmented generation grounds large language models in external evidence, but most pipelines still treat retrieved passages as deterministic and mutually consistent context. In open information environments, retrieved sources may disagree because of temporal drift, source error, ambiguity, or genuine uncertainty. This paper introduces ERAG, an uncertainty-aware RAG framework that converts retrieved chunks into probabilistic evidence before generation. A lightweight evaluator extracts candidate claims and maps chunk-level support to Dirichlet evidence. A conflict-preserving Dempster-Shafer fusion rule then transfers unresolved disagreement into epistemic uncertainty rather than normalizing it away. The generator is routed to direct answering, conflict-aware answering, or abstention according to the fused uncertainty score. Experiments on CRAG, ConflictQA, and MuSiQue show that ERAG remains competitive with the strongest matched baseline on standard question answering while improving behavior under conflict. On the CRAG ambiguous subset, hallucination decreases from 45.3% for Corrective RAG to a human-calibrated estimate of 34.8%, conflict resolution increases from 35.2% to 51.2%, and expected calibration error improves to 0.122. These results suggest that evidential modeling is a practical mechanism for trustworthy information processing in foundation-model-based retrieval systems.
