Keywords
retrieval self-check
distractor density
paired simulation
reproducibility
Abstract
We evaluated retrieval self-check for retrieval-augmented answering under 22% distractor density. A deterministic paired simulation generated 72 cases and preserved a rare-condition slice. Mean evidence faithfulness changed from 0.496 to 0.538; the paired difference was +0.041 (95% interval +0.039 to +0.044). 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
Takamura, T., & Umezawa, A. (2025). Privacy-Preserving Retrieval-Augmented Generation on Local Devices for Regenerative Medicine Applications. https://doi.org/10.1101/2025.10.20.25337146
Liu, L. (2026). A Survey of (Deep RAG) Deep Retrieval Augmented Generation and Reasoning in Large Language Models. https://doi.org/10.36227/techrxiv.177272838.89432844/v1
Joseph, A. (2025). Reducing Hallucinations in Large Language Models Through Integrated Self-Verification and Retrieval-Augmented Generation. Volume 2B: 45th Computers and Information in Engineering Conference (CIE), V02BT02A032. https://doi.org/10.1115/detc2025-169730
Quintela, J., & Sapateiro, M. (2024). Retrieval-Augmented Generation in Large Language Models through Selective Augmentation. https://doi.org/10.21203/rs.3.rs-4652959/v1
Farizi, A. A., Arsi, P., & Subarkah, P. (2026). Comparative Performance of Retrieval Augmented Generation Tourism Chatbots. Indonesian Journal of Innovation Studies, 27(1). https://doi.org/10.21070/ijins.v27i1.1836
Shetty, R. (2025). Enhancing Context-Aware Search with Retrieval-Augmented Generation. https://doi.org/10.36227/techrxiv.174060240.09460752/v1
Köhler, A., Stein, M., & Vogt, E. (2026). Adaptive Context Reconstruction for Enhanced Retrieval Augmented Generation . https://doi.org/10.2139/ssrn.6101386
Samal, M. P. (2026). A Theoretical Analysis of Self-Contained Retrieval-Augmented Generation with Small Language Models. https://doi.org/10.36227/techrxiv.177219989.96070478/v1
Budha, K., & Lagun, N. (2026). Operationalizing Reliability Gaps in Large Language Models: A Semi-Systematic Evidence Map of Reasoning, Factuality, Evaluation, and Retrieval-Augmented Generation. https://doi.org/10.21203/rs.3.rs-9882260/v1