Keywords
retrieval self-check
distractor density
paired simulation
reproducibility
Abstract
We evaluated retrieval self-check for retrieval-augmented answering under 42% distractor density. A deterministic paired simulation generated 72 cases and preserved a rare-condition slice. Mean evidence faithfulness changed from 0.498 to 0.540; the paired difference was +0.042 (95% interval +0.040 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
Pukhampuang, A. (2026). A Governance-First Architecture for Multi-Tenant Retrieval-Augmented Generation. https://doi.org/10.2139/ssrn.6211238
Zhu, J., & Tong, Y. (2026). Dynamic Multi-Hop Retrieval-Augmented Generation Framework for Professional Domain Question Answering. https://doi.org/10.22541/au.177499050.00368942/v1
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
Hou, Y., & Zhang, R. (2024). Enhancing Dietary Supplement Question Answer via Retrieval-Augmented Generation (RAG) with LLM. https://doi.org/10.1101/2024.09.11.24313513
Fasolino, I. (2026). In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning. https://doi.org/10.32388/7hxkqe
Dhanda, K. (2026). MedRAG: Retrieval-Augmented Generation for Medical QA-Comparing Base and RAG-Augmented LLM Performance on Evidence from Peer-Reviewed Clinical Research. https://doi.org/10.2139/ssrn.6608518
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
Zandigohar, M., & Dai, Y. (2026). RAGulate: Retrieval-Augmented Generation for Post-hoc Literature-Grounded Regulatory Assessment. https://doi.org/10.64898/2026.01.20.700704
Liu, C. (2025). Retrieval-Augmented Generation. https://doi.org/10.31224/5781