Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lu, Zhixiang, Su, Jionglong
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PRISM: A Personality-Driven Multi-Agent Framework for Social Media Simulation
by: Lu, Zhixiang, et al.
Published: (2025)

Causal-SAM-LLM: Large Language Models as Causal Reasoners for Robust Medical Segmentation
by: Tang, Tao, et al.
Published: (2025)

Counterfactual Debating with Preset Stances for Hallucination Elimination of LLMs
by: Fang, Yi, et al.
Published: (2024)

SAGE: Sustainable Agent-Guided Expert-tuning for Culturally Attuned Translation in Low-Resource Southeast Asia
by: Lu, Zhixiang, et al.
Published: (2026)

Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning
by: Liao, Yiming, et al.
Published: (2026)

Combating Adversarial Attacks with Multi-Agent Debate
by: Chern, Steffi, et al.
Published: (2024)

MERIT: Multilingual Expert-Reward Informed Tuning for Chinese-Centric Low-Resource Machine Translation
by: Lu, Zhixiang, et al.
Published: (2026)

Counterfactual Probing for Hallucination Detection and Mitigation in Large Language Models
by: Feng, Yijun
Published: (2025)

What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal Models
by: Kim, Junho, et al.
Published: (2024)

A Multi-Agent Framework for Mitigating Dialect Biases in Privacy Policy Question-Answering Systems
by: Klisura, Đorđe, et al.
Published: (2025)

Decoding the Flow: CauseMotion for Emotional Causality Analysis in Long-form Conversations
by: Zhang, Yuxuan, et al.
Published: (2025)

Mitigating Hallucination on Hallucination in RAG via Ensemble Voting
by: Xie, Zequn, et al.
Published: (2026)

Counterfactual Segmentation Reasoning: Diagnosing and Mitigating Pixel-Grounding Hallucination
by: Li, Xinzhuo, et al.
Published: (2025)

Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization
by: Zhang, Siyuan, et al.
Published: (2025)

Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations
by: Li, Shuo, et al.
Published: (2025)

Mitigating Object Hallucination via Concentric Causal Attention
by: Xing, Yun, et al.
Published: (2024)

Towards Detecting LLMs Hallucination via Markov Chain-based Multi-agent Debate Framework
by: Sun, Xiaoxi, et al.
Published: (2024)

Removal of Hallucination on Hallucination: Debate-Augmented RAG
by: Hu, Wentao, et al.
Published: (2025)

MedFact: A Large-scale Chinese Dataset for Evidence-based Medical Fact-checking of LLM Responses
by: Chen, Tong, et al.
Published: (2025)

Mitigating Prompt-Induced Hallucinations in Large Language Models via Structured Reasoning
by: Hao, Jinbo, et al.
Published: (2026)

Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate
by: Yao, Binwei, et al.
Published: (2025)

Mitigating Object Hallucination via Robust Local Perception Search
by: Gao, Zixian, et al.
Published: (2025)

MedHallTune: An Instruction-Tuning Benchmark for Mitigating Medical Hallucination in Vision-Language Models
by: Yan, Qiao, et al.
Published: (2025)

Multi-Agent Dialectical Refinement for Enhanced Argument Classification
by: Bąba, Jakub, et al.
Published: (2026)

MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate
by: Amayuelas, Alfonso, et al.
Published: (2024)

Counterfactual Graph for Multi-Agent LLM Calibration
by: Huang, Jiatan, et al.
Published: (2026)

Enhancing Multi-Agent Debate System Performance via Confidence Expression
by: Lin, Zijie, et al.
Published: (2025)

MedDialBench: Benchmarking LLM Diagnostic Robustness under Parametric Adversarial Patient Behaviors
by: Luo, Xiaotian, et al.
Published: (2026)

Learning from Self-Debate: Preparing Reasoning Models for Multi-Agent Debate
by: Liu, Chenxi, et al.
Published: (2026)

CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models
by: Poppi, Tobia, et al.
Published: (2026)

RedDebate: Safer Responses Through Multi-Agent Red Teaming Debates
by: Asad, Ali, et al.
Published: (2025)

Hallucination Detection and Hallucination Mitigation: An Investigation
by: Luo, Junliang, et al.
Published: (2024)

Multi-agent Undercover Gaming: Hallucination Removal via Counterfactual Test for Multimodal Reasoning
by: Liang, Dayong, et al.
Published: (2025)

Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking
by: Cheng, Xiaoxue, et al.
Published: (2025)

A Debate-Driven Experiment on LLM Hallucinations and Accuracy
by: Li, Ray, et al.
Published: (2024)

Mitigating Text Toxicity with Counterfactual Generation
by: Bhan, Milan, et al.
Published: (2024)

Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinations
by: Lu, Yifan, et al.
Published: (2025)

CODMAS: A Dialectic Multi-Agent Collaborative Framework for Structured RTL Optimization
by: Chang, Che-Ming, et al.
Published: (2026)

Improving Clinical Diagnosis with Counterfactual Multi-Agent Reasoning
by: You, Zhiwen, et al.
Published: (2026)

MedAction: Towards Active Multi-turn Clinical Diagnostic LLMs
by: Hsu, Hsin-Ling, et al.
Published: (2026)