Keywords
retrieval self-check
distractor density
paired simulation
reproducibility
Abstract
We evaluated retrieval self-check for retrieval-augmented answering under 43% distractor density. A deterministic paired simulation generated 72 cases and preserved a median slice. Mean evidence faithfulness changed from 0.542 to 0.582; the paired difference was +0.040 (95% interval +0.038 to +0.042). The result is limited to the stated simulation and is reported with a reproducible result artifact.
References
Sang, Y. (2025). Robustness of Fine-Tuned Llms Under Noisy Retrieval Inputs. 2025 6th International Conference on Artificial Intelligence and Electromechanical Automation (AIEA), 417-420. https://doi.org/10.1109/aiea66061.2025.11160531
Aryani, A. (2024). A Brief Introduction to Retrieval Augmented Generation (RAG). https://doi.org/10.59350/8mwjx-hry76
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.v1
Kim, M. H. (2026). Pool-Gated Retrieval: Beyond Retrieval-Augmented Generation Toward Accountable Evidential Admission. https://doi.org/10.20944/preprints202606.0414.v1
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
Madhurima, M. (2026). FaithGate: A Proposed Architecture for Real-Time Hallucination Detection and Correction in Retrieval-Augmented Generation Systems. https://doi.org/10.2139/ssrn.7242858
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
Martin, T., & Gilchrist, S. (2026). A2JRAG: Process-Aware Retrieval-Augmented Generation for Public Legal Information Systems. https://doi.org/10.2139/ssrn.7114139
Garg, A., & Esposito, J. (2026). Operationalizing Evidence Admissibility in Retrieval-Augmented Generation: The DCA-TRAG Architecture. https://doi.org/10.2139/ssrn.7111618
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