Keywords
retrieval self-check
distractor density
paired simulation
reproducibility
Abstract
We evaluated retrieval self-check for retrieval-augmented answering under 13% distractor density. A deterministic paired simulation generated 72 cases and preserved a upper-severity quartile. Mean evidence faithfulness changed from 0.580 to 0.632; the paired difference was +0.053 (95% interval +0.051 to +0.055). 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
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
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
Kumar, C., Deshmukh, S., Khatter, H., Kumar, B., & Pal, Y. (2026). ACW-RC: Adaptive Confidence-Weighted Retrieval Correction for Robust Augmented Generation. https://doi.org/10.2139/ssrn.6546797
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
Aryani, A. (2024). A Brief Introduction to Retrieval Augmented Generation (RAG). https://doi.org/10.59350/8mwjx-hry76
Hou, X., & Wang, X. (2024). Large Language Model with Federated Retrieval-Augmented Generation for Improved Knowledge Retrieval. https://doi.org/10.36227/techrxiv.171837853.31531482/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
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
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