Keywords
retrieval self-check
distractor density
paired simulation
reproducibility
Abstract
We evaluated retrieval self-check for retrieval-augmented answering under 30% distractor density. A deterministic paired simulation generated 72 cases and preserved a low-signal stratum. Mean evidence faithfulness changed from 0.497 to 0.545; the paired difference was +0.048 (95% interval +0.046 to +0.050). 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
Ibiloye, A. C. (2025). Long Text Language Ensemble Models: Extension of Retrieval-Augmented Generation (RAG). https://doi.org/10.31219/osf.io/b94ng_v1
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
Kim, M. H. (2026). Pool-Gated Retrieval: Beyond Retrieval-Augmented Generation Toward Accountable Evidential Admission. https://doi.org/10.20944/preprints202606.0414.v1
Bo, L., Duan, R., Shi, S., Sun, X., Lin, Z., & Ji, W. (2026). GIANT: Leveraging Retrieval-Augmented Generation for Automated Bug Reproduction Test Generation. https://doi.org/10.2139/ssrn.7269657
Glendenning, J. (2026). Is Retrieval-Augmented Generation Fair Use?. https://doi.org/10.2139/ssrn.6165167
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
Aryani, A. (2024). A Brief Introduction to Retrieval Augmented Generation (RAG). https://doi.org/10.59350/ayxyj-h9751
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
Dhenia, R. N. K., Sridhar, R., & Kanani, I. J. (2024). Retrieval-Augmented Generation: Enhancing Reliability in Large Language Models. American International Journal of Computer Science and Technology, 6, 46-49. https://doi.org/10.63282/3117-5481/aijcst-v6i2p105