Towards Reliable Medical LLMs: Benchmarking and Enhancing Confidence Estimation of Large Language Models in Medical Consultation

• URL: http://arxiv.org/abs/2601.15645v1
• Date: Thu, 22 Jan 2026 04:51:39 GMT
• Title: Towards Reliable Medical LLMs: Benchmarking and Enhancing Confidence Estimation of Large Language Models in Medical Consultation
• Abstract summary: We propose the first benchmark for assessing confidence in multi-turn interaction during realistic medical consultations.<n>Our benchmark unifies three types of medical data for open-ended diagnostic generation.<n>We present MedConf, an evidence-grounded linguistic self-assessment framework.
• Score: 97.36081721024728
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large-scale language models (LLMs) often offer clinical judgments based on incomplete information, increasing the risk of misdiagnosis. Existing studies have primarily evaluated confidence in single-turn, static settings, overlooking the coupling between confidence and correctness as clinical evidence accumulates during real consultations, which limits their support for reliable decision-making. We propose the first benchmark for assessing confidence in multi-turn interaction during realistic medical consultations. Our benchmark unifies three types of medical data for open-ended diagnostic generation and introduces an information sufficiency gradient to characterize the confidence-correctness dynamics as evidence increases. We implement and compare 27 representative methods on this benchmark; two key insights emerge: (1) medical data amplifies the inherent limitations of token-level and consistency-level confidence methods, and (2) medical reasoning must be evaluated for both diagnostic accuracy and information completeness. Based on these insights, we present MedConf, an evidence-grounded linguistic self-assessment framework that constructs symptom profiles via retrieval-augmented generation, aligns patient information with supporting, missing, and contradictory relations, and aggregates them into an interpretable confidence estimate through weighted integration. Across two LLMs and three medical datasets, MedConf consistently outperforms state-of-the-art methods on both AUROC and Pearson correlation coefficient metrics, maintaining stable performance under conditions of information insufficiency and multimorbidity. These results demonstrate that information adequacy is a key determinant of credible medical confidence modeling, providing a new pathway toward building more reliable and interpretable large medical models.

Related papers

• SMILE: Self-Explainable Multimodal Information Bottleneck for Medical Diagnosis [71.98702207668346]
  Explainability is increasingly seen as a crucial requirement in AI-based medical diagnosis, particularly in safety-critical clinical decision-making.<n>This paper addresses the problem of self-explainable multimodal diagnosis by formulating it within the information bottleneck (IB) framework.<n>We propose a unified learning paradigm that jointly optimize predictive performance and modality-specific explainability.
  arXiv  Detail & Related papers  (2026-09-04T14:13:24Z)
• Beyond the Leaderboard: Design Lessons for Trustworthy Multimodal VQA [4.080704298118247]
  multimodal AI must combine visual and textual evidence while remaining reliable and interpretable.<n>We analyze design choices across nine documented systems for question answering and explanation quality.<n>The findings support trustworthy multimodal healthcare AI based on data fusion, explainability, and resilient evaluation.
  arXiv  Detail & Related papers  (2026-07-16T17:38:19Z)
• Beyond Semantics: An Evidential Reasoning-Aware Multi-View Learning Framework for Trustworthy Mental Health Prediction [22.40813291181261]
  Automated mental health prediction using textual data has shown promising results with deep learning and large language models.<n>Existing approaches largely rely on semantic representations and often produce overconfident predictions under ambiguous, noisy, or shifted data.<n>We propose a multi-view learning problem that integrates semantic information from encoder-only models with higher-level reasoning information from decoder-only models.
  arXiv  Detail & Related papers  (2026-05-06T16:49:17Z)
• Towards Trustworthy Depression Estimation via Disentangled Evidential Learning [50.22167852149165]
  We propose EviDep, an evidential learning framework that jointly quantifies depression severity.<n>EviDep enforces strict information integrity to guarantee robust evidence synthesis.<n>It achieves state-of-the-art predictive accuracy and superior uncertainty calibration, delivering a robust fail-safe mechanism for trustworthy clinical screening.
  arXiv  Detail & Related papers  (2026-04-17T13:27:11Z)
• Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction [72.89352076103889]
  Large language models (LLMs) achieve high accuracy in medical diagnosis when all clinical information is provided in a single turn.<n>We introduce MINT, a high-fidelity, multi-turn medical diagnosis benchmark comprising 1,035 cases.<n>We uncover three persistent behavioral patterns that significantly impact diagnostic decisions.
  arXiv  Detail & Related papers  (2026-04-06T00:23:10Z)
• FedAgain: A Trust-Based and Robust Federated Learning Strategy for an Automated Kidney Stone Identification in Ureteroscopy [6.025561073248826]
  This paper introduces FedAgain, a trust-based Federated Learning (Federated Learning) strategy designed to enhance robustness and generalization for automated kidney stone identification from endoscopic images.<n>The framework enables the training of collaborative models across multiple institutions while preserving data privacy and promoting stable convergence under real-world conditions.
  arXiv  Detail & Related papers  (2026-03-19T22:40:37Z)
• Benchmarking Egocentric Clinical Intent Understanding Capability for Medical Multimodal Large Language Models [48.95516224614331]
  We introduce MedGaze-Bench, the first benchmark leveraging clinician gaze as a Cognitive Cursor to assess intent understanding across surgery, emergency simulation, and diagnostic interpretation.<n>Our benchmark addresses three fundamental challenges: visual homogeneity of anatomical structures, strict temporal-causal dependencies in clinical, and implicit adherence to safety protocols.
  arXiv  Detail & Related papers  (2026-01-11T02:20:40Z)
• MediEval: A Unified Medical Benchmark for Patient-Contextual and Knowledge-Grounded Reasoning in LLMs [7.2159153945746795]
  Existing evaluations either test factual medical knowledge in isolation or assess patient-level reasoning without verifying correctness, leaving a critical gap.<n>We introduce MediEval, a benchmark that links MIMIC-IV electronic health records to a unified knowledge base built from UMLS and other biomedical vocabularies.<n> MediEval generates diverse factual and counterfactual medical statements within real patient contexts, enabling systematic evaluation across a 4-quadrant framework.
  arXiv  Detail & Related papers  (2025-12-23T22:52:24Z)
• A Multi-faceted Analysis of Cognitive Abilities: Evaluating Prompt Methods with Large Language Models on the CONSORT Checklist [1.1731001328350983]
  This study applies a behavioral and metacognitive analytic approach using an expert-validated dataset.<n>We analyze both cognitive adaptation and calibration error using metrics: Expected Error (ECE) and a baseline-normalized Relative Error (RCE)<n>Our results reveal pronounced miscalibration and overconfidence in both models, especially under clinical role-playing conditions.
  arXiv  Detail & Related papers  (2025-10-22T00:15:02Z)
• Proactive Reasoning-with-Retrieval Framework for Medical Multimodal Large Language Models [15.530083855947987]
  We propose the first Multimodal Medical Reasoning-with-Retrieval framework, Med-RwR.<n>Med-RwR actively retrieves external knowledge by querying observed symptoms or domain-specific medical concepts during reasoning.<n> Evaluation on various public medical benchmarks demonstrates Med-RwR's significant improvements over baseline models.
  arXiv  Detail & Related papers  (2025-10-21T05:18:18Z)
• KnowGuard: Knowledge-Driven Abstention for Multi-Round Clinical Reasoning [44.49237466254508]
  In clinical practice, physicians refrain from making decisions when patient information is insufficient.<n>This behavior, known as abstention, is a critical safety mechanism preventing potentially harmful misdiagnoses.<n>We propose KnowGuard, a novel paradigm that integrates systematic knowledge graph exploration for clinical decision-making.
  arXiv  Detail & Related papers  (2025-09-29T14:03:01Z)
• Knowing or Guessing? Robust Medical Visual Question Answering via Joint Consistency and Contrastive Learning [34.6490677122246]
  We show that current Medical Vision-Language Models (Med-VLMs) exhibit concerning fragility in Medical Visual Question Answering.<n>We propose Consistency and Contrastive Learning (CCL), which integrates knowledge-anchored consistency learning and bias-aware contrastive learning.<n>CCL achieves SOTA performance on three popular VQA benchmarks and notably improves answer consistency by 50% on the challenging RoMed test set.
  arXiv  Detail & Related papers  (2025-08-26T05:21:19Z)
• Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models [52.2001050216955]
  Existing methods aim to enhance the performance of Medical Vision Language Model (MedVLM) by adjusting model structure, fine-tuning with high-quality data, or through preference fine-tuning.<n>We propose an expert-in-the-loop framework named Expert-Controlled-Free Guidance (Expert-CFG) to align MedVLM with clinical expertise without additional training.
  arXiv  Detail & Related papers  (2025-07-12T09:03:30Z)
• Uncertainty-aware abstention in medical diagnosis based on medical texts [87.88110503208016]
  This study addresses the critical issue of reliability for AI-assisted medical diagnosis.<n>We focus on the selection prediction approach that allows the diagnosis system to abstain from providing the decision if it is not confident in the diagnosis.<n>We introduce HUQ-2, a new state-of-the-art method for enhancing reliability in selective prediction tasks.
  arXiv  Detail & Related papers  (2025-02-25T10:15:21Z)
• Which Client is Reliable?: A Reliable and Personalized Prompt-based Federated Learning for Medical Image Question Answering [51.26412822853409]
  We present a novel personalized federated learning (pFL) method for medical visual question answering (VQA) models. Our method introduces learnable prompts into a Transformer architecture to efficiently train it on diverse medical datasets without massive computational costs.
  arXiv  Detail & Related papers  (2024-10-23T00:31:17Z)
• StratMed: Relevance Stratification between Biomedical Entities for Sparsity on Medication Recommendation [9.296433860766165]
  StratMed is a stratification strategy that overcomes the long-tailed problem and achieves fuller learning of sparse data. It also utilizes a dual-property network to address the issue of mutual constraints on the safety and accuracy of medication combinations. Our model reduces safety risk by 15.08%, improves accuracy by 0.36%, and reduces training time consumption by 81.66%.
  arXiv  Detail & Related papers  (2023-08-31T14:59:32Z)
• Towards Reliable Medical Image Segmentation by Modeling Evidential Calibrated Uncertainty [57.023423137202485]
  Concerns regarding the reliability of medical image segmentation persist among clinicians.<n>We introduce DEviS, an easily implementable foundational model that seamlessly integrates into various medical image segmentation networks.<n>By leveraging subjective logic theory, we explicitly model probability and uncertainty for medical image segmentation.
  arXiv  Detail & Related papers  (2023-01-01T05:02:46Z)
• UNITE: Uncertainty-based Health Risk Prediction Leveraging Multi-sourced Data [81.00385374948125]
  We present UNcertaInTy-based hEalth risk prediction (UNITE) model. UNITE provides accurate disease risk prediction and uncertainty estimation leveraging multi-sourced health data. We evaluate UNITE on real-world disease risk prediction tasks: nonalcoholic fatty liver disease (NASH) and Alzheimer's disease (AD) UNITE achieves up to 0.841 in F1 score for AD detection, up to 0.609 in PR-AUC for NASH detection, and outperforms various state-of-the-art baselines by up to $19%$ over the best baseline.
  arXiv  Detail & Related papers  (2020-10-22T02:28:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.