Keywords
retrieval self-check
distractor density
paired simulation
reproducibility
Abstract
We evaluated retrieval self-check for retrieval-augmented answering under 8% distractor density. A deterministic paired simulation generated 72 cases and preserved a rare-condition slice. Mean evidence faithfulness changed from 0.539 to 0.588; the paired difference was +0.049 (95% interval +0.046 to +0.051). 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
Martin, T., & Gilchrist, S. (2026). A2JRAG: Process-Aware Retrieval-Augmented Generation for Public Legal Information Systems. https://doi.org/10.2139/ssrn.7114139
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
Procko, T., & Ochoa, O. (2024). Graph Retrieval-Augmented Generation for Large Language Models: A Survey. https://doi.org/10.2139/ssrn.4895062
Farizi, A. A., Arsi, P., & Subarkah, P. (2026). Comparative Performance of Retrieval Augmented Generation Tourism Chatbots. Indonesian Journal of Innovation Studies, 27(1). https://doi.org/10.21070/ijins.v27i1.1836
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
Quintela, J., & Sapateiro, M. (2024). Retrieval-Augmented Generation in Large Language Models through Selective Augmentation. https://doi.org/10.21203/rs.3.rs-4652959/v1
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
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
Genesis, J. (2025). Retrieval-Augmented Text Generation: Methods, Challenges, and Applications. https://doi.org/10.20944/preprints202504.0443.v1