Abstract
Standard Retrieval-Augmented Generation (RAG) 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 $\text{lambda}(s)$ based on its source type, and retrieval scores are reweighted using: $$\text{score}(q, d) = \text{sim}(q, d) \times \text{lambda}(s)$$. 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.
Blogger's Review: This study introduces a significant enhancement to RAG processes by incorporating source reliability priors, leading to a remarkable increase in document retrieval accuracy. This innovative approach not only improves the reliability of generative models but also opens new avenues for future research, making it worthy of attention.