给检索增强生成加了个可信度权重，提升答案可靠性。
Source-Aware Reranking for Retrieval-Augmented Generation: A Reliability Prior Approach
- 按来源类型给文档打可信度分，再与语义相似度相乘重排。
- 在健康领域数据集上，前5项精确率从0.48升至0.72。
- 适合关注生成结果可信度的医疗、新闻等场景使用。
标准的检索增强生成管道仅依据语义相似度排序检索文档，未考虑来源出处或可信度。本文提出一种简单可解释的修改：在检索排名中引入基于领域的源可信度先验。每个文档根据其来源类型被赋予一个先验权重λ(s)，最终得分计算为score(q, d) = sim(q, d) * λ(s)。在包含120篇文档的健康领域语料库上，该方法与仅依赖相似度的基线相比，将Precision@5从0.48提升至0.72，并在所评估的对抗威胁模型下显著降低低可信度来源文档的检索概率。所有实验均在密尔沃基工程学院的高性能计算集群Rosie上完成，该平台提供GPU加速基础设施，确保实验的可靠与可复现。结果表明，在当前实验设置范围内，该方法可作为缓解RAG中源质量下降问题的有效策略。
原文摘要 · Abstract (English)
Standard Retrieval-Augmented Generation pipelines rank retrieved documents by semantic similarity alone, without accounting for source provenance or credibility. This work evaluates a simple and interpretable modification to RAG retrieval ranking that incorporates domain-informed source reliability priors. Each document is assigned a prior lambda(s) based on its source type, and retrieval scores are reweighted using score(q, d) = sim(q, d) * lambda(s). The framework is evaluated against a similarity-only baseline on a 120-document health-domain corpus. In this controlled setting, source-aware reranking improves Precision@5 from 0.48 to 0.72 and reduces average adversarial document retrieval under the evaluated threat model, where low-credibility sources are identifiable via metadata. All experiments were executed on Rosie, the high-performance computing cluster at the Milwaukee School of Engineering, which provided the GPU-accelerated infrastructure necessary to run the full experimental pipeline reliably and reproducibly. These results suggest a potential mitigation strategy for source quality degradation in RAG pipelines, within the limits of the experimental setup described.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。