Problem
Research questions and friction points this paper is trying to address.
medical error detection
error correction
large language models
patient safety
healthcare applications
MedGuards: Multi-Agent System for Reliable Medical Error Detection and Correction
🤖 AI Summary
This work addresses the safety risks posed by minor errors in large language models (LLMs) when generating medical text, a critical concern given the limited generalizability of existing error detection and correction methods. The authors propose an interpretable, fine-tuning-free multi-agent framework that decomposes the task into three collaborative agents responsible for error detection, localization, and correction. A confidence-guided arbitration mechanism integrates reasoning traces and model confidence to make robust decisions. Additionally, they introduce a novel evaluation metric—Keyword-Priority Correction Score (KPCS)—to more accurately assess the fidelity of critical medical information. Evaluated across four multilingual clinical note datasets, the proposed approach consistently outperforms state-of-the-art methods across diverse LLMs and evaluation metrics, demonstrating significant promise for enabling safer deployment of LLMs in healthcare settings.
📝 Abstract
As Large Language Models (LLMs) are increasingly deployed in healthcare settings, accurate error detection and correction in generated or existing text becomes critical, as even minor mistakes can pose risks to patient safety. Existing methods for error detection and correction, including automated checks and heuristic-based approaches, do not generalize well across unseen datasets. In this paper, we propose MedGuards as a medical safety guardrail, which is a new framework that treats medical error detection and correction as a multi-agent in-context learning task. Specialized agents separately detect, localize, and correct errors, while a confidence-guided arbitration mechanism resolves disagreements using reasoning traces and confidence scores. This design enhances interpretability, robustness, and adaptability, without requiring additional training of the base LLMs. Additionally, we introduce the Keyword-Prioritized Correction Score (KPCS), a new evaluation metric that considers whether critical keywords within the reference text are generated correctly, providing a more comprehensive assessment than conventional metrics. Experiments across four multilingual medical datasets consisting of clinical notes demonstrate significant improvements by the proposed framework across several metrics and models. Our aim is to enable safer deployment of LLMs in real-world healthcare applications. For reproducibility, we make our code publicly available at https://github.com/congboma/MedErrBench.
Innovation
Methods, ideas, or system contributions that make the work stand out.
multi-agent system
medical error correction
in-context learning
confidence-guided arbitration
Keyword-Prioritized Correction Score
🔎 Similar Papers
No similar papers found.
