Collaboration among Multiple Large Language Models for Medical Question Answering

2025/05/22 by Shang, Kexin, Chia‐Hsuan Chang, Chang, Chia-Hsuan +2
Computer Science · Medicine · #Artificial Intelligence (cs.AI) #Artificial Intelligence in Healthcare and Education #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2505.16648

openalex publication_date 2025/05/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Empowered by vast internal knowledge reservoir, the new generation of large language models (LLMs) demonstrate untapped potential to tackle medical tasks. However, there is insufficient effort made towards summoning up a synergic effect from multiple LLMs' expertise and background. In this study, we propose a multi-LLM collaboration framework tailored on a medical multiple-choice questions dataset. Through post-hoc analysis on 3 pre-trained LLM participants, our framework is proved to boost all LLMs reasoning ability as well as alleviate their divergence among questions. We also measure an LLM's confidence when it confronts with adversary opinions from other LLMs and observe a concurrence between LLM's confidence and prediction accuracy.

Citations

• Counterfactual Debating with Preset Stances for Hallucination Elimination of LLMs
• Med42 -- Evaluating Fine-Tuning Strategies for Medical LLMs: Full-Parameter vs. Parameter-Efficient Approaches
• Debating with More Persuasive LLMs Leads to More Truthful Answers
• Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration
• Mixtral of Experts
• MEDITRON-70B: Scaling Medical Pretraining for Large Language Models
• Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting
• Large Language Models Cannot Self-Correct Reasoning Yet
• Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• Improving Factuality and Reasoning in Language Models through Multiagent Debate
• QLoRA: Efficient Finetuning of Quantized LLMs
• Clinical Camel: An Open Expert-Level Medical Language Model with Dialogue-Based Knowledge Encoding
• MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data
• Capabilities of GPT-4 on Medical Challenge Problems
• Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models
• Large Language Models are Zero-Shot Reasoners
• Self-Consistency Improves Chain of Thought Reasoning in Language Models
• BNAI, NO-TOKEN, and MIND-UNITY: Pillars of a Systemic Revolution in Artificial Intelligence

Related

• CURE: Confidence-driven Unified Reasoning Ensemble Framework for Medical Question Answering
• Can large language models reason about medical questions?
• Enhancing Healthcare through Large Language Models: A Study on Medical Question Answering
• Large language models encode clinical knowledge
• Do Large Language Models have Shared Weaknesses in Medical Question Answering?