ArgMed-Agents: Explainable Clinical Decision Reasoning with LLM Disscusion via Argumentation Schemes

2024-03-10

AI Summary

To address the opacity, lack of verifiability, and insufficient explainability of large language models (LLMs) in clinical decision-making, this paper proposes a multi-agent self-iterative debate framework grounded in clinical argumentation patterns. Methodologically, it formally embeds argumentation schemes into LLM reasoning, constructs directed argument graphs to model conflicting viewpoints, and integrates a symbolic logic solver for automated verification of rational consistency. The key contributions are: (1) the first realization of an argumentation-scheme-driven, self-explanatory clinical debate mechanism for LLMs; and (2) a synergistic framework unifying argument graph structure with symbolic reasoning, ensuring both interpretability and formal guarantee of correctness. Experiments on complex clinical decision tasks demonstrate that our approach outperforms state-of-the-art prompting techniques in accuracy, while significantly improving user trust, explanation quality, and logical coherence of reasoning.

Technology Category

• Knowledge Representation and Reasoning: Argumentation
• Multiagent Systems: Agreement, Argumentation & Negotiation
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

There are two main barriers to using large language models (LLMs) in clinical reasoning. Firstly, while LLMs exhibit significant promise in Natural Language Processing (NLP) tasks, their performance in complex reasoning and planning falls short of expectations. Secondly, LLMs use uninterpretable methods to make clinical decisions that are fundamentally different from the clinician's cognitive processes. This leads to user distrust. In this paper, we present a multi-agent framework called ArgMed-Agents, which aims to enable LLM-based agents to make explainable clinical decision reasoning through interaction. ArgMed-Agents performs self-argumentation iterations via Argumentation Scheme for Clinical Discussion (a reasoning mechanism for modeling cognitive processes in clinical reasoning), and then constructs the argumentation process as a directed graph representing conflicting relationships. Ultimately, use symbolic solver to identify a series of rational and coherent arguments to support decision. We construct a formal model of ArgMed-Agents and present conjectures for theoretical guarantees. ArgMed-Agents enables LLMs to mimic the process of clinical argumentative reasoning by generating explanations of reasoning in a self-directed manner. The setup experiments show that ArgMed-Agents not only improves accuracy in complex clinical decision reasoning problems compared to other prompt methods, but more importantly, it provides users with decision explanations that increase their confidence.

Problem

• Medical Decision Making
• Large Language Models
• Explainable AI

Innovation

• ArgMed-Agents
• Medical Decision-Making
• Large Language Models