Keywords
retrieval self-check
distractor density
paired simulation
reproducibility
Abstract
We evaluated retrieval self-check for retrieval-augmented answering under 34% distractor density. A deterministic paired simulation generated 72 cases and preserved a boundary-condition stratum. Mean evidence faithfulness changed from 0.498 to 0.551; the paired difference was +0.053 (95% interval +0.050 to +0.055). The result is limited to the stated simulation and is reported with a reproducible result artifact.
References
Sang, Y. (2025). Towards Explainable RAG: Interpreting the Influence of Retrieved Passages on Generation. 2025 4th International Conference on Robotics, Artificial Intelligence and Intelligent Control (RAIIC), 397-400. https://doi.org/10.1109/raiic65850.2025.11170170
Qu, J., & Luo, F. (2026). Research on Citizen Privacy Risk Assessment Method Based on Retrieval-Augmented Generation. https://doi.org/10.21203/rs.3.rs-9015963/v1
Garg, A., & Esposito, J. (2026). Operationalizing Evidence Admissibility in Retrieval-Augmented Generation: The DCA-TRAG Architecture. https://doi.org/10.2139/ssrn.7111618
Fu, E. L. (2025). Industrial AI Guardrails: Solving Field Service Reliability with Retrieval-Augmented Generation. Global Business & Economics Journal. https://doi.org/10.70924/f83n6wqz/g91xh08t
Srivastava, M. (2026). A Privacy-First Architecture for Fully Local Retrieval-Augmented Generation in Secure Document Intelligence. https://doi.org/10.36227/techrxiv.176800894.46972585/v1
Martin, T., & Gilchrist, S. (2026). A2JRAG: Process-Aware Retrieval-Augmented Generation for Public Legal Information Systems. https://doi.org/10.2139/ssrn.7114139
Roy, P., & Singirikonda, A. (2026). Optimization and Constraint Modeling using LLMs with a Retrieval Augmented Generation Process. https://doi.org/10.2139/ssrn.7068218
Fasolino, I. (2026). In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning. https://doi.org/10.32388/7hxkqe
Genesis, J. (2025). Retrieval-Augmented Text Generation: Methods, Challenges, and Applications. https://doi.org/10.20944/preprints202504.0443.v1
Ibiloye, A. C. (2025). Long Text Language Ensemble Models: Extension of Retrieval-Augmented Generation (RAG). https://doi.org/10.31219/osf.io/b94ng_v1