Dialectic-Med: Mitigating Diagnostic Hallucinations via Counterfactual Adversarial Multi-Agent Debate

• URL: http://arxiv.org/abs/2604.11258v1
• Date: Mon, 13 Apr 2026 10:09:36 GMT
• Title: Dialectic-Med: Mitigating Diagnostic Hallucinations via Counterfactual Adversarial Multi-Agent Debate
• Abstract summary: We propose Dialectic-Med, a multi-agent framework that enforces diagnostic rigor through adversarial dialectics.<n>By explicitly modeling the cognitive process of falsification, our framework guarantees that diagnostic reasoning is tightly grounded in verified visual regions.
• Score: 2.645243404278707
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Large Language Models (MLLMs) in healthcare suffer from severe confirmation bias, often hallucinating visual details to support initial, potentially erroneous diagnostic hypotheses. Existing Chain-of-Thought (CoT) approaches lack intrinsic correction mechanisms, rendering them vulnerable to error propagation. To bridge this gap, we propose Dialectic-Med, a multi-agent framework that enforces diagnostic rigor through adversarial dialectics. Unlike static consensus models, Dialectic-Med orchestrates a dynamic interplay between three role-specialized agents: a proponent that formulates diagnostic hypotheses; an opponent equipped with a novel visual falsification module that actively retrieves contradictory visual evidence to challenge the Proponent; and a mediator that resolves conflicts via a weighted consensus graph. By explicitly modeling the cognitive process of falsification, our framework guarantees that diagnostic reasoning is tightly grounded in verified visual regions. Empirical evaluations on MIMIC-CXR-VQA, VQA-RAD, and PathVQA demonstrate that Dialectic-Med not only achieves state-of-the-art performance but also fundamentally enhances the trustworthiness of the reasoning process. Beyond accuracy, our approach significantly enhances explanation faithfulness and decisively mitigates hallucinations, establishing a new standard over single-agent baselines.

Related papers

• Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation [66.62662330558906]
  CORAL is a multimodal framework that integrates spatial grounding and concept-level supervision into a unified reasoning process.<n>CORAL employs a prompt-driven medical segmentation model to localize lesions and predicts multi-class clinical attributes through a Concept Bottleneck module.<n>Experiments on BUS-CoT and IU X-ray datasets demonstrate consistent improvements in diagnostic accuracy, concept consistency, and report quality over strong general-purpose and medical MLLMs.
  arXiv  Detail & Related papers  (2026-09-14T10:21:23Z)
• MAGIS: Evidence-Based Multi-Agent Reasoning for Interpretable Strabismus Clinical Decision-Making [18.234379859242406]
  Strabismus is a common ocular disorder that requires fine-grained subtype diagnosis for individualized treatment planning.<n>We propose MAGIS, an evidence-based Multi-AGent reasoning for Interpretable Strabismus diagnosis framework.
  arXiv  Detail & Related papers  (2026-06-08T09:21:53Z)
• Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming [41.40761036883243]
  Vision-Language Models (VLMs) have significantly advanced medical visual question answering, yet their performance in ultrasound remains suboptimal.<n>We propose a framework specifically designed to consider the sonographer's cognitive workflow.<n>We first introduce a structured Zoom-then-Diagnose paradigm, which replicates the interactive search process to enable lesion-focused reasoning.
  arXiv  Detail & Related papers  (2026-05-20T19:06:34Z)
• Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models [65.57985131861399]
  hallucinations are strongly correlated with cognitive bifurcation points that often exhibit high entropy states.<n>We propose V-STAR, a lightweight, holistic training paradigm designed to internalize visually aware reasoning capabilities.
  arXiv  Detail & Related papers  (2026-04-11T13:59:05Z)
• MedCausalX: Adaptive Causal Reasoning with Self-Reflection for Trustworthy Medical Vision-Language Models [10.466505116993451]
  Existing medical chain-of-thought models lack explicit mechanisms to represent and enforce causal reasoning.<n>We propose MedCausalX, an end-to-end framework explicitly models causal reasoning chains in medical VLMs.<n>We show that MedCausalX consistently outperforms state-of-the-art methods, improving diagnostic consistency by +5.4 points, reducing hallucination by over 10 points, and attaining top spatial grounding IoU.
  arXiv  Detail & Related papers  (2026-03-24T11:28:15Z)
• Clinical Cognition Alignment for Gastrointestinal Diagnosis with Multimodal LLMs [63.535652574541764]
  Multimodal Large Language Models (MLLMs) have demonstrated remarkable potential in medical image analysis.<n>Their application in gastrointestinal endoscopy is currently hindered by two critical limitations.<n>We propose a novel Clinical-Cognitive-Aligned (CogAlign) framework to address these challenges.
  arXiv  Detail & Related papers  (2026-03-21T07:47:37Z)
• Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models [62.932580559941414]
  Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements.<n>We propose a new paradigm for diagnosing hallucinations, recasting them from static output errors into dynamic pathologies of a model's computational cognition.
  arXiv  Detail & Related papers  (2026-03-16T17:20:38Z)
• Making medical vision-language models think causally across modalities with retrieval-augmented cross-modal reasoning [16.243806723551454]
  Medical vision-language models (VLMs) achieve strong performance in diagnostic reporting and image-text alignment.<n>Their underlying reasoning mechanisms remain fundamentally correlational, exhibiting reliance on superficial statistical associations.<n>We propose Multimodal Causal Retrieval-Augmented Generation, a framework that integrates causal inference principles with multimodal retrieval.
  arXiv  Detail & Related papers  (2026-01-26T11:03:00Z)
• AgentsEval: Clinically Faithful Evaluation of Medical Imaging Reports via Multi-Agent Reasoning [73.50200033931148]
  We introduce AgentsEval, a multi-agent stream reasoning framework that emulates the collaborative diagnostic workflow of radiologists.<n>By dividing the evaluation process into interpretable steps including criteria definition, evidence extraction, alignment, and consistency scoring, AgentsEval provides explicit reasoning traces and structured clinical feedback.<n> Experimental results demonstrate that AgentsEval delivers clinically aligned, semantically faithful, and interpretable evaluations that remain robust under paraphrastic, semantic, and stylistic perturbations.
  arXiv  Detail & Related papers  (2026-01-23T11:59:13Z)
• When One Modality Sabotages the Others: A Diagnostic Lens on Multimodal Reasoning [22.39245479538899]
  We introduce modality sabotage, a diagnostic failure mode in which a high-confidence unimodal error overrides other evidence and misleads the fused result.<n>A model-agnostic evaluation layer treats each modality as an agent, producing candidate labels and a brief self-assessment used for auditing.<n>A simple fusion mechanism aggregates these outputs, exposing contributors (modalities supporting correct outcomes) and saboteurs (modalities that mislead)
  arXiv  Detail & Related papers  (2025-11-04T18:20:13Z)
• MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning [52.064286116035134]
  We develop MedAlign, a framework to ensure visually accurate LVLM responses for Medical Visual Question Answering (Med-VQA)<n>We first propose a multimodal Direct Preference Optimization (mDPO) objective to align preference learning with visual context.<n>We then design a Retrieval-Aware Mixture-of-Experts (RA-MoE) architecture that utilizes image and text similarity to route queries to a specialized and context-augmented LVLM.
  arXiv  Detail & Related papers  (2025-10-24T02:11:05Z)
• MedMMV: A Controllable Multimodal Multi-Agent Framework for Reliable and Verifiable Clinical Reasoning [35.97057940590796]
  We introduce MedMMV, a controllable multi-agent framework for reliable and verifiable clinical reasoning.<n>On six medical benchmarks, MedMMV improves accuracy by up to 12.7% and, more critically, demonstrates superior reliability.
  arXiv  Detail & Related papers  (2025-09-29T05:51:25Z)
• Leveraging Imperfection with MEDLEY A Multi-Model Approach Harnessing Bias in Medical AI [42.798415096963396]
  Bias in medical artificial intelligence is conventionally viewed as a defect requiring elimination.<n>We propose MEDLEY, a conceptual framework that orchestrates multiple AI models while preserving their diverse outputs.<n>Unlike traditional approaches that suppress disagreement, MEDLEY documents model-specific biases as potential strengths.
  arXiv  Detail & Related papers  (2025-08-29T14:12:03Z)
• Silence is Not Consensus: Disrupting Agreement Bias in Multi-Agent LLMs via Catfish Agent for Clinical Decision Making [80.94208848596215]
  We present a new concept called Catfish Agent, a role-specialized LLM designed to inject structured dissent and counter silent agreement.<n>Inspired by the catfish effect'' in organizational psychology, the Catfish Agent is designed to challenge emerging consensus to stimulate deeper reasoning.
  arXiv  Detail & Related papers  (2025-05-27T17:59:50Z)

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.