Keywords
retrieval self-check
distractor density
paired simulation
reproducibility
Abstract
We evaluated retrieval self-check for retrieval-augmented answering under 21% distractor density. A deterministic paired simulation generated 72 cases and preserved a low-signal stratum. Mean evidence faithfulness changed from 0.576 to 0.617; the paired difference was +0.041 (95% interval +0.039 to +0.043). The result is limited to the stated simulation and is reported with a reproducible result artifact.
References
Sang, Y. (2025). AutoCrit: A Meta-Reasoning Framework for Self-Critique and Iterative Error Correction in LLM Chains-of-Thought. 2025 6th International Conference on Machine Learning and Computer Application (ICMLCA), 1177-1180. https://doi.org/10.1109/icmlca66850.2025.11336788
Roy, P., & Roy, D. (2025). Building a Security and Reliability Evaluation Suite for Retrieval-Augmented Generation (RAG) Systems. https://doi.org/10.20944/preprints202510.0418.v2
Maharana, P. R., Verma, A., & Joshi, K. (2025). Retrieval augmented generation for building datasets from scientific literature. https://doi.org/10.26434/chemrxiv-2024-qjx32-v2
Ji, S., Zhang, X., Huang, Y., & Li, D. (2026). CGS-RAG:Community-Aggregated Graph Semantic Retrieval-Augmented Generation. https://doi.org/10.21203/rs.3.rs-9748268/v1
Alvaro, A. (2026). Graph-Native Intelligence: A Novel Architecture for Multi-Source Knowledge Synthesis Beyond Retrieval Augmented Generation. https://doi.org/10.2139/ssrn.6335438
Alabi Bankole, S., & Kayode Saheed, Y. (2026). ADAPTIVE MULTI-STAGE VECTOR RETRIEVAL FOR RETRIEVAL-AUGMENTED GENERATION. NLP & Big Data, 79-98. https://doi.org/10.5121/csit.2026.1601307
НИЧ, & ПРАВОРСЬКА (2026). RAG (RETRIEVAL-AUGMENTED GENERATION) ЯК НОВА ПАРАДИГМА КОРПОРАТИВНОЇ АВТОМАТИЗАЦІЇ. Herald of Khmelnytskyi National University. Technical sciences, 361(1), 375-382. https://doi.org/10.31891/2307-5732-2026-361-53
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
Xiong, X., & Zheng, M. (2024). Merging Mixture of Experts and Retrieval Augmented Generation for Enhanced Information Retrieval and Reasoning. https://doi.org/10.21203/rs.3.rs-3978298/v1
Kim, M. H. (2026). Pool-Gated Retrieval: Beyond Retrieval-Augmented Generation Toward Accountable Evidential Admission. https://doi.org/10.20944/preprints202606.0414.v1