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

arXiv:2604.11258v1 Announce Type: new 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

• See Fair, Speak Truth: Equitable Attention Improves Grounding and Reduces Hallucination in Vision-Language Alignment
• Self-Debias: Self-correcting for Debiasing Large Language Models
• GenProve: Learning to Generate Text with Fine-Grained Provenance
• FAITH: Factuality Alignment through Integrating Trustworthiness and Honestness
• Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?

Source: arXiv cs.CL | 2026-04-14