The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Dialogical AI for Cognitive Bias Mitigation in Medical Diagnosis
Abstract
Large Language Models (LLMs) promise to enhance clinical decision-making, yet empirical studies reveal a paradox: physician performance with LLM assistance shows minimal improvement or even deterioration. This failure stems from an “acquiescence problem”: current LLMs passively confirm rather than challenge clinicians’ hypotheses, reinforcing cognitive biases such as anchoring and premature closure. To address these limitations, we propose a Dialogic Reasoning Framework that operationalizes Dialogical AI principles through a prototype implementation named “Diagnostic Dialogue” (DiDi). This framework operationalizes LLMs into three user-controlled roles: the Framework Coach (guiding structured reasoning), the Socratic Guide (asking probing questions), and the Red Team Partner (presenting evidence-based alternatives). Built upon Retrieval-Augmented Generation (RAG) architecture for factual grounding and traceability, this framework transforms LLMs from passive information providers into active reasoning partners that systematically mitigate cognitive bias. We evaluate the feasibility and qualitative impact of this framework through a pilot study (DiDi) deployed at Centro Chirurgico Toscano (CCT). Through purposive sampling of complex clinical scenarios, we present comparative case studies illustrating how the dialogic approach generates necessary cognitive friction to overcome acquiescence observed in standard LLM interactions. While rigorous clinical validation through randomized controlled trials remains necessary, this work establishes a methodological foundation for designing LLM-based clinical decision support systems that genuinely augment human clinical reasoning.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Effect of Clinical Decision-Support Systems: A Systematic Review
Bright, T. J., Wong, A., Dhurjati, R., Bristow, E., Bastian, L., Coeytaux, R. R., Samsa, G., Hasselblad, V., Williams, J. W., Musty, M. D., et al. (2012) · Annals of Internal Medicine · doi:10.7326/0003-4819-157-1-201207030-00450 · Cited by 1,200
Large language models in healthcare and medical domain: A review
Nazi, Z. A., & Peng, W. (2024) · Informatics · doi:10.3390/informatics11030057 · Cited by 415
Research works printed but not linked: 26
- Goh, 2024, Large language model influence on diagnostic reasoning: A randomized clinical trial, JAMA Netw. Open, 7, e2440969, 10.1001/jamanetworkopen.2024.40969 · DOI · Paper page
- Hager, 2024, Evaluation and mitigation of the limitations of large language models in clinical decision-making, Nat. Med., 30, 2613, 10.1038/s41591-024-03097-1 · DOI · Paper page
- Boon, 2021, From clinical decision support to clinical reasoning support systems, J. Eval. Clin. Pract., 27, 520, 10.1111/jep.13541 · DOI
- Hundley, 2002, The importance of pilot studies, Nurs. Stand., 16, 33
- Wang, 2023, Exploring medical students’ metacognitive and regulatory dimensions of diagnostic problem solving, Med. Educ. Online, 28, 2210804, 10.1080/10872981.2023.2210804 · DOI
- Shinn, 2023, Reflexion: Language agents with verbal reinforcement learning, Adv. Neural Inf. Process. Syst., 36, 8634
- Du, Y., Li, S., Torralba, A., Tenenbaum, J.B., and Mordatch, I. (2024, January 21–27). Improving factuality and reasoning in language models through multiagent debate. Proceedings of the Forty-First International Conference on Machine Learning, Vienna, Austria.
- Aththanagoda, A., Kulathilake, K., and Abdullah, N. (2025). Precision and Personalization: How Large Language Models Redefining Diagnostic Accuracy in Personalized Medicine—A Systematic Literature Review. IEEE J. Biomed. Health Inform., online ahead of print. · DOI
- Artsi, Y., Sorin, V., Glicksberg, B.S., Korfiatis, P., Freeman, R., Nadkarni, G.N., and Klang, E. (2025). Challenges of Implementing LLMs in Clinical Practice: Perspectives. J. Clin. Med., 14. · DOI
- Singh, C., Inala, J.P., Galley, M., Caruana, R., and Gao, J. (2024). Rethinking interpretability in the era of large language models. arXiv.
- Roustan, 2025, The clinicians’ guide to large language models: A general perspective with a focus on hallucinations, Interact. J. Med. Res., 14, e59823, 10.2196/59823 · DOI · Paper page
- Omar, 2025, Multi-model assurance analysis showing large language models are highly vulnerable to adversarial hallucination attacks during clinical decision support, Commun. Med., 5, 330, 10.1038/s43856-025-01021-3 · DOI · Paper page
- Harrer, 2023, Attention is not all you need: The complicated case of ethically using large language models in healthcare and medicine, eBioMedicine, 90, 104512, 10.1016/j.ebiom.2023.104512 · DOI · Paper page
- Schmidgall, 2024, Evaluation and mitigation of cognitive biases in medical language models, npj Digit. Med., 7, 295, 10.1038/s41746-024-01283-6 · DOI · Paper page
- Roeschl, 2025, Assessing the limitations of large language models in clinical practice guideline–concordant treatment decision-making on real-world data: Retrospective study, JMIRx Med, 6, e74899, 10.2196/74899 · DOI
- Park, Y.J., Pillai, A., Deng, J., Guo, E., Gupta, M., Paget, M., and Naugler, C. (2024). Assessing the research landscape and clinical utility of large language models: A scoping review. BMC Med. Inform. Decis. Mak., 24. · DOI · Paper page
- Whelehan, 2020, Medicine and heuristics: Cognitive biases and medical decision-making, Ir. J. Med. Sci., 189, 1477, 10.1007/s11845-020-02235-1 · DOI
- Vicente, 2025, Machine learning systems as mentors in human learning: A user study on machine bias transmission in medical training, Int. J. Hum.-Comput. Stud., 198, 103474, 10.1016/j.ijhcs.2025.103474 · DOI
- Ye, A., Moore, J., Novick, R., and Zhang, A.X. (2024). Language models as critical thinking tools: A case study of philosophers. arXiv.
- Miao, 2025, Improving Large Language Model Applications in the Medical and Nursing Domains With Retrieval-Augmented Generation: Scoping Review, J. Med. Internet Res., 27, e80557, 10.2196/80557 · DOI · Paper page
- Cabitza, 2025, Let XAI generate reliability metadata, not medical explanations, Comput. Methods Programs Biomed., 273, 109090, 10.1016/j.cmpb.2025.109090 · DOI
- Rosenbacke, 2024, How explainable artificial intelligence can increase or decrease clinicians’ trust in AI applications in health care: Systematic review, JMIR AI, 3, e53207, 10.2196/53207 · DOI · Paper page
- Ouyang, 2022, Training language models to follow instructions with human feedback, Adv. Neural Inf. Process. Syst., 35, 27730
- Bai, Y., Kadavath, S., Kundu, S., Askell, A., Kernion, J., Jones, A., Chen, A., Goldie, A., Mirhoseini, A., and McKinnon, C. (2022). Constitutional ai: Harmlessness from ai feedback. arXiv.
- Nori, H., Daswani, M., Kelly, C., Lundberg, S., Ribeiro, M.T., Wilson, M., Liu, X., Sounderajah, V., Carlson, J., and Lungren, M.P. (2025). Sequential Diagnosis with Language Models. arXiv.
- Song, Z., Lu, J., Du, Y., Yu, B., Pruyn, T.M., Huang, Y., Guo, K., Luo, X., Qu, Y., and Qu, Y. (2025). Evaluating Large Language Models in Scientific Discovery. arXiv.
Metadata
- Authors
- Guiducci, L., Saulle, C., Dimitri, G. M., Valli, B., Alpini, S., Tenti, C., & Rizzo, A.
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2026-01-09
- Volume
- 16
- Issue
- 2
- Pages
- 710
- ISSN
- 2076-3417
- Cited by
- 5
- References
- 2
- Language
- en
- Funders
- Tuscuny Region, Italy (Programma regionale FESR Toscana OP1 OS1 Az 1.1.4)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.