Uncertainty-Calibrated Retrieval-Augmented Generation for Clinical Decision Support and Medical Risk Assessment
Keywords:
retrieval-augmented generation, clinical decision support, uncertainty calibration, medical risk assessment, trustworthy artificial intelligence, health informatics governanceAbstract
Retrieval-augmented generation has emerged as a promising architecture for grounding large language models in external evidence, yet clinical decision support demands more than factual grounding. It requires calibrated expressions of uncertainty, traceable evidence pathways, and governance mechanisms that can withstand regulatory, ethical, and operational scrutiny. This paper examines uncertainty-calibrated retrieval-augmented generation as a socio-technical infrastructure for clinical decision support and medical risk assessment. It analyzes retrieval architecture, evidence ranking, calibration signals, human workflow integration, and deployment constraints. The discussion emphasizes that uncertainty calibration cannot be treated as a late-stage model patch. Instead, it must be designed into data curation, retrieval indexing, generation policies, interface design, monitoring, and accountability structures. The paper further considers fairness, robustness, sustainability, and policy implications, arguing that clinical retrieval systems must distinguish between epistemic uncertainty, aleatoric uncertainty, and institutional uncertainty. Cross-domain comparisons with open-domain question answering, legal retrieval, and enterprise search illustrate both transferable patterns and domain-specific hazards. The conclusion proposes that trustworthy clinical retrieval systems require layered governance, continuous calibration audits, and explicit escalation pathways to human clinicians. Such systems should not replace clinical judgment but should make the limits of machine-generated evidence synthesis visible, contestable, and operationally actionable.
References
1. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 33, 9459–9474.
2. Borgeaud, S., Mensch, A., Hoffmann, J., Cai, T., Rutherford, E., Millican, K., van den Driessche, G., Lespiau, J. B., Damoc, B., Clark, A., de Las Casas, D., Guy, A., Menick, J., Ring, R., Hennigan, T., Huang, S., Maggiore, L., Jones, C., Cassirer, A., ... Sifre, L. (2022). Improving language models by retrieving from trillions of tokens. Proceedings of the 39th International Conference on Machine Learning, 162, 2206–2240.
3. Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., & Wang, H. (2023). Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997.
4. Guu, K., Lee, K., Tung, Z., Pasupat, P., & Chang, M. (2020). Retrieval augmented language model pre-training. Proceedings of the 37th International Conference on Machine Learning, 119, 3929–3938.
5. Izacard, G., & Grave, E. (2021). Leveraging passage retrieval with generative models for open domain question answering. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, 874–880.
6. Karpukhin, V., Oğuz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., & Yih, W. (2020). Dense passage retrieval for open-domain question answering. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 6769–6781.
7. Thorne, J., Vlachos, A., Christodoulopoulos, C., & Mittal, A. (2018). FEVER: A large-scale dataset for fact extraction and verification. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 809–819.
8. Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., & Mané, D. (2016). Concrete problems in AI safety. arXiv preprint arXiv:1606.06565.
9. Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2019). Dissecting racial bias in an algorithm used to manage the health of populations. Science, 366(6464), 447–453.
10. Char, D. S., Shah, N. H., & Magnus, D. (2018). Implementing machine learning in health care—Addressing ethical challenges. New England Journal of Medicine, 378(11), 981–983.
11. Topol, E. J. (2019). High-performance medicine: The convergence of human and artificial intelligence. Nature Medicine, 25(1), 44–56.
12. Zhang, R. (2025, December). Uncertainty-Aware RAG: Trustworthy Generation and Risk Control. In 2025 5th International Symposium on Artificial Intelligence and Big Data (AIBDF) (pp. 526-531). IEEE.
13. Kendall, A., & Gal, Y. (2017). What uncertainties do we need in Bayesian deep learning for computer vision? Advances in Neural Information Processing Systems, 30, 5574–5584.
14. Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017). On calibration of modern neural networks. Proceedings of the 34th International Conference on Machine Learning, 70, 1321–1330.
15. Ovadia, Y., Fertig, E., Ren, J., Nado, Z., Sculley, D., Nowozin, S., Dillon, J. V., Lakshminarayanan, B., & Snoek, J. (2019). Can you trust your model's uncertainty? Evaluating predictive uncertainty under dataset shift. Advances in Neural Information Processing Systems, 32, 13991–14002.
16. Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016). SQuAD: 100,000+ questions for machine comprehension of text. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 2383–2392.
17. Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., Payne, P., Seneviratne, M., Gamble, P., Kelly, C., Babiker, A., Schärli, N., Chowdhery, A., Mansfield, P., Demner-Fushman, D., ... Natarajan, V. (2023). Large language models encode clinical knowledge. Nature, 620(7972), 172–180.
18. Thirunavukarasu, A. J., Ting, D. S. J., Elangovan, K., Gutierrez, L., Tan, T. F., & Ting, D. S. W. (2023). Large language models in medicine. Nature Medicine, 29(8), 1930–1940.
19. Sallam, M. (2023). ChatGPT utility in healthcare education, research, and practice: Systematic review on the promising perspectives and valid concerns. Healthcare, 11(6), 887.
20. Price, W. N., & Cohen, I. G. (2019). Privacy in the age of medical big data. Nature Medicine, 25(1), 37–43.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Computational Intelligence Systems
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.