Layered Hallucination Evaluation for Medical Question Answering Across Medical RAG Pipelines
Keywords:
Retrieval-Augmented Generation, Medical Question Answering, Hallucination Evaluation, Large Language ModelsAbstract
The integration of large language models into healthcare contexts has precipitated a paradigm shift in clinical decision support and patient information acquisition. However, the propensity of these models to generate factually incorrect information, commonly referred to as hallucinations, poses severe risks in medical applications where accuracy is paramount. Retrieval-augmented generation systems have been proposed to mitigate this issue by grounding model responses in external, authoritative knowledge bases. Despite their promise, retrieval-augmented medical question answering systems still exhibit complex hallucination patterns that traditional evaluation metrics fail to adequately capture. This paper introduces a comprehensive, layered evaluation framework designed specifically to dissect and quantify hallucinations across multiple stages of the retrieval-augmented generation pipeline. By decomposing the system into retrieval, reasoning, and generation layers, the proposed methodology isolates the origin of factual inaccuracies, offering a granular perspective on systemic failures. We provide an extensive theoretical background, detail the specific mechanisms of the layered framework, and present a rigorous analysis of its application in simulated clinical scenarios. The findings suggest that a layered evaluation approach significantly improves the correlation with expert human judgment compared to holistic, end-to-end evaluation metrics. This research contributes to the broader objective of developing safer, more reliable artificial intelligence tools for the medical domain by establishing a structured methodology for diagnosing and resolving source-conflicting hallucinations.
References
1. Sang, Y. (2025, August). Robustness of fine-tuned llms under noisy retrieval inputs. In 2025 6th International Conference on Artificial Intelligence and Electromechanical Automation (AIEA) (pp. 417-420). IEEE.
2. Deng, L., Deng, S., Chen, Y., Dai, Y., Zhong, Z., Li, L., ... & Huang, H. (2026). Tool-Augmented Agent for Closed-loop Optimization, Simulation, and Modeling Orchestration. arXiv preprint arXiv:2605.20190.
3. Zhou, D. (2026). AI-Driven Hybrid SAST–DAST–SCA–IAST Framework for Risk-Based Vulnerability Prioritization in Microservice Architectures.
4. Chen, L. (2026). Beyond external constraints: The missing dimension of ai governance. Available at SSRN 6449738.
5. Ma, Y., Qu, D., & Pyrozhenko, M. (2026). Bio-RegNet: A Meta-Homeostatic Bayesian Neural Network Framework Integrating Treg-Inspired Immunoregulation and Autophagic Optimization for Adaptive Community Detection and Stable Intelligence. Biomimetics, 11(1), 48.
6. Huang, Z., Wang, J., Chen, L., Xiao, B., Cai, L., Zeng, Y., & Xu, J. (2025, October). MVISU-Bench: Benchmarking Mobile Agents for Real-World Tasks by Multi-App, Vague, Interactive, Single-App and Unethical Instructions. In Proceedings of the 33rd ACM International Conference on Multimedia (pp. 8797-8805).
7. Li, X., Wang, P., Li, G., Ni, L., & Zhang, Y. (2023). Design of interface circuits and lightweight PUF for TMR sensors. IEEE Sensors Journal, 23(11), 11754-11761.
8. Zhou, D. (2025, December). M-VP2: Microservice-Oriented Vulnerability Patch Planning-A Cost-Aware Approachusing Multi-Agent Reinforcement Learning. In 2025 5th International Conference on Computer, Internet of Things and Control Engineering (CITCE) (pp. 248-254). IEEE.
9. Xu, X., Tu, W., & Yang, Y. (2023). CASE-Net: Integrating local and non-local attention operations for speech enhancement. Speech Communication, 148, 31-39.
10. Sang, Y. (2025, October). AutoCrit: A Meta-Reasoning Framework for Self-Critique and Iterative Error Correction in LLM Chains-of-Thought. In 2025 6th International Conference on Machine Learning and Computer Application (ICMLCA) (pp. 1177-1180). IEEE.
11. Z. Hang, Y. Yashengjiang, J. Li, H. Dong, Y. Wei, Z. Hao, J. Ma, S. Bai, H. Kai, X. Yue, G. Si, D. Jiang, C. Yao, Z. Hu, J. Zhang, P. Liu, Y. Shen, X. Ren, L. Liu, Z. Xu, H. Li, Q. Yao, H. Dong, and H. Wang, “PDEAgent-Bench: A multi-metric, multi-library benchmark for PDE solver generation,” arXiv preprint arXiv:2605.09636, 2026, doi: 10.48550/arXiv.2605.09636.
12. Zhou, J., Shuang, K., Wang, Q., Qian, B., & Guo, J. (2025). Bi-directional feature learning-based approach for zero-shot event argument extraction. Information Processing & Management, 62(5), 104199.
13. Liang, H., Huang, C., Xu, Y., Tang, C., Ye, W., Zhang, J., ... & Xu, L. (2024). Llava-slt: Visual language tuning for sign language translation. arXiv preprint arXiv:2412.16524.
14. Liang, X., Tao, M., Xia, Y., Wang, J., Li, K., Wang, Y., ... & Wang, X. (2025). Sage: Self-evolving agents with reflective and memory-augmented abilities. Neurocomputing, 647, 130470.
15. Guo, J., Yang, L., Chen, P., Xiao, Q., Wang, Y., Juan, X., ... & Wang, M. (2025). GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators. arXiv preprint arXiv:2512.19682.
16. Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2020). Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21(140), 1–67.
17. Zhang, Jiaquan, et al. "Lightweight llm agent memory with small language models." arXiv preprint arXiv:2604.07798 (2026).
18. Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., et al. (2023). Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288.
19. Wang, J., Zhao, R., Wei, W., Wang, Y., Yu, M., Zhou, J., ... & Xu, L. (2026, March). Comorag: A cognitive-inspired memory-organized rag for stateful long narrative reasoning. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 40, No. 39, pp. 33557-33565).
20. Niu, Ke, et al. "Cme-cad: Heterogeneous collaborative multi-expert reinforcement learning for cad code generation." arXiv preprint arXiv:2512.23333 (2025).
21. Zhu, R., Jiang, Z., Wu, J., Ma, Z., Song, J., Bai, F., ... & He, C. (2025, April). Grait: Gradient-driven refusal-aware instruction tuning for effective hallucination mitigation. In Findings of the Association for Computational Linguistics: NAACL 2025 (pp. 4006-4021).
22. Zhu, R., Ma, Z., Wu, J., Gao, J., Wang, J., Lin, D., & He, C. (2025, April). Utilize the flow before stepping into the same river twice: Certainty represented knowledge flow for refusal-aware instruction tuning. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 24, pp. 26157-26165).
23. Qian, B., Guo, J., Wang, Q., & Shuang, K. (2025). From local verification to global reasoning: Exploiting slot-accompanying update for improved slot selection. Knowledge-Based Systems, 319, 113521.
24. Vinyals, O., Fortunato, M., & Jaitly, N. (2015). Pointer networks. In Advances in Neural Information Processing Systems.
25. Xiao, Q., & Zhou, K. (2026). MACD: Model-Aware Contrastive Decoding via Counterfactual Data. arXiv preprint arXiv:2602.01740.
26. Yang, Y., Yang, X., Jiang, Y., Mu, N., Hu, H., Xie, R., ... & Xu, B. (2026). GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent Systems. arXiv preprint arXiv:2602.15776.
27. Wang, Chenxing, et al. "When & How to Write for Personalized Demand-aware Query Rewriting in Video Search." arXiv preprint arXiv:2602.17667 (2025).
28. Mao, C., Shuang, K., Guo, J., Qian, B., Yang, Y., & Li, H. (2026). Cognition-aligned frequency filtering for sentence embeddings. Information Processing & Management, 63(2), 104415.
29. Pennington, J., Socher, R., & Manning, C. D. (2014). GloVe: Global vectors for word representation. In Proceedings of EMNLP.
30. Luong, M.-T., Pham, H., & Manning, C. D. (2015). Effective approaches to attention-based neural machine translation. In Proceedings of EMNLP.
31. Wang, S., Zhang, X., Wang, P., & Li, X. (2026). Design of Magnetic Sensor Array-Based PUFs for IoT Security. IEEE Transactions on Instrumentation and Measurement, 75, 1-9.
32. Qu, D., & Ma, Y. (2025). Magnet-bn: markov-guided Bayesian neural networks for calibrated long-horizon sequence forecasting and community tracking. Mathematics, 13(17), 2740.
33. Guo, J., Shuang, K., Zhang, K., Liu, Y., Li, J., & Wang, Z. (2023, June). Learning to imagine: distillation-based interactive context exploitation for dialogue state tracking. In Proceedings of the AAAI conference on artificial intelligence (Vol. 37, No. 11, pp. 12845-12853).
34. Li, S. (2025). Momentum, volume and investor sentiment study for us technology sector stocks—A hidden markov model based principal component analysis. PloS one, 20(9), e0331658.
35. Wang, Juyuan, et al. "HeadRank: Decoding-Free Passage Reranking via Preference-Aligned Attention Heads." arXiv preprint arXiv:2604.17237 (2026).
36. Xu, X., Wang, Y., Xu, D., Peng, Y., Zhang, C., Jia, J., & Chen, B. (2022, May). Vsegan: Visual speech enhancement generative adversarial network. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 7308-7311). IEEE.
37. Zhang, K., Shuang, K., Yang, X., Yao, X., & Guo, J. (2023, July). What is overlap knowledge in event argument extraction? APE: A cross-datasets transfer learning model for EAE. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 393-409).
38. Shen, B., Wang, Y., Shang, D., & Ning, T. (2026). Self-Commitment Latency: A Reward-Free Probe for Prompted Implicit Hacking. Publication date: 2026-06-04.
39. Zhang, Jiaquan, et al. "Learning global hypothesis space for enhancing synergistic reasoning chain." arXiv preprint arXiv:2602.09794 (2026).
40. Chen, Y., Zhao, C., & Gao, Y. (2025). Blockchain applications in health insurance: a review of applications, challenges, and prospects. Frontiers in Blockchain, 8, 1699290.
41. Zhang, W., & Pei, S. (2026). Predictive prefetching for retrieval-augmented generation. Proceedings of Machine Learning Research. The Forty-third International Conference on Machine Learning, ICML 2026. https://par.nsf.gov/biblio/10686293
42. Lv, Z., Wang, Q., Lyu, T., & Dong, J. (2026). A Deep Learning-Based Model for User Emotion Recognition and Behavior Guidance Design: EMoGuideNet-An Emotion-Aware Multimodal Framework for Enhancing Intelligent User Interaction. Journal of Organizational and End User Computing (JOEUC), 38(1), 1-30.
43. Sang, Y. (2025, July). Towards explainable rag: Interpreting the influence of retrieved passages on generation. In 2025 4th International Conference on Robotics, Artificial Intelligence and Intelligent Control (RAIIC) (pp. 397-400). IEEE.
44. Deng, L., Guo, H., Bai, Y., Dai, Y., Huang, H., & Shi, Y. (2025). BrepLLM: Native Boundary Representation Understanding with Large Language Models. arXiv preprint arXiv:2512.16413.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Eliza Baker, Graham Ward, Nadia Masri
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
