Skip to content

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

Conference: ACL 2026 arXiv: 2604.11258 Code: N/A Area: Causal Inference Keywords: Medical Hallucination, Multi-Agent Debate, Counterfactual Reasoning, Visual Falsification, Confirmation Bias

TL;DR

Dialectic-Med, inspired by Popperian falsificationism, uses three-agent adversarial dialectical reasoning (proposer for diagnostic hypotheses, opponent with visual falsification module for proactively retrieving contradictory visual evidence, and mediator with weighted consensus graph), achieving SOTA on MIMIC-CXR-VQA, VQA-RAD, and PathVQA with 12.5% explanation faithfulness improvement.

Method

Key Designs

  1. Visual Falsification Module (VFM): Given hypothesis \(H_t\), the opponent generates counterfactual probe queries \(Q_{cf}\) and uses PubMedCLIP to compute attention maps \(M_{cf}\) locating contradictory evidence in images.

  2. Dynamic Consensus Graph: Nodes represent diagnostic hypotheses or visual evidence; edges encode support/refute logical relations with confidence weights. Includes cycle detection to prevent hypothesis loops.

  3. Attack Strength Threshold Termination: Debate terminates when \(S_{attack} < \theta_{thresh}\), indicating the current hypothesis has withstood falsification attempts.

Key Experimental Results

  • SOTA across all three medical VQA benchmarks
  • 12.5% explanation faithfulness improvement
  • Visual falsification is the key differentiator vs pure semantic debate

Highlights & Insights

  • Operationalizing Popperian falsificationism as an AI system design principle: actively seeking disconfirming evidence rather than just supporting evidence
  • VFM grounds debate in concrete image regions rather than language games
  • Direct value for medical AI safety as a safeguard layer before clinical deployment

Rating

  • Novelty: ⭐⭐⭐⭐⭐
  • Experimental Thoroughness: ⭐⭐⭐⭐
  • Writing Quality: ⭐⭐⭐⭐⭐
  • Value: ⭐⭐⭐⭐⭐