CiteGuard-RAG 系统提升证据引用准确性
CiteGuard-RAG: A Validation-Centered AI System for Evidence-Grounded Question Answering
这个系统很实用，能帮你生成更可靠的答案，特别是对于需要引用证据的领域，比如法律或研究，推荐试试。
这篇论文提出 CiteGuard-RAG 系统，通过混合语义-词法检索、引用约束生成和句子级验证，解决 RAG 系统中答案缺乏证据支撑的问题。在住房法数据集等测试中，该系统实现了 99.1% 的检索准确率、98.3% 的接地回答准确率和 98.3% 的引用有效性，验证环节能有效防止幻觉。
CiteGuard-RAG: A Validation-Centered AI System for Evidence-Grounded Question Answering
Retrieval-augmented generation (RAG) can improve access to complex information; however, retrieving evidence alone does not ensure that answers are grounded, citation-valid, or appropriately refused. This paper introduces CiteGuard-RAG, a validation-centered AI system for evidence-grounded question answering. The system integrates hybrid semantic-lexical retrieval, citation-constrained generation, sentence-level grounding validation, and single-pass regeneration. Validation is used at runtime to determine whether a candidate answer should be accepted, refused, or regenerated before final delivery. CiteGuard-RAG is evaluated on 400 questions across a controlled housing-law dataset, PrivacyQA, and CUAD. In the controlled evaluation, it achieves 99.1% retrieval accuracy, 98.3% grounded-answer accuracy, and 98.3% citation validity, with no validation-detected hallucinations. Ablation results show that grounded-answer accuracy drops sharply when validation is removed, even when retrieval accuracy remains unchanged. External evaluation shows that while citation validity remains strong, evidence utilization, span alignment, and refusal calibration become harder under domain shift. These findings indicate that trustworthy RAG systems require explicit validation between retrieval and final answer delivery. CiteGuard-RAG provides a practical architecture for linking retrieval, generation, citation checking, abstention, and regeneration in high-stakes information access.
