Abstract:Advancements in large language models (LLMs) have paved the way for LLM-based agent systems that offer enhanced accuracy and interpretability across various domains. Radiology, with its complex analytical requirements, is an ideal field for the application of these agents. This paper aims to investigate the pre-requisite question for building concrete radiology agents which is, `Can modern LLMs act as agent cores in radiology environments?' To investigate it, we introduce RadABench with three-fold contributions: First, we present RadABench-Data, a comprehensive synthetic evaluation dataset for LLM-based agents, generated from an extensive taxonomy encompassing 6 anatomies, 5 imaging modalities, 10 tool categories, and 11 radiology tasks. Second, we propose RadABench-EvalPlat, a novel evaluation platform for agents featuring a prompt-driven workflow and the capability to simulate a wide range of radiology toolsets. Third, we assess the performance of 7 leading LLMs on our benchmark from 5 perspectives with multiple metrics. Our findings indicate that while current LLMs demonstrate strong capabilities in many areas, they are still not sufficiently advanced to serve as the central agent core in a fully operational radiology agent system. Additionally, we identify key factors influencing the performance of LLM-based agent cores, offering insights for clinicians on how to apply agent systems in real-world radiology practices effectively. All of our code and data are open-sourced in https://github.com/MAGIC-AI4Med/RadABench.
Abstract:In this study, we present MedS-Bench, a comprehensive benchmark designed to evaluate the performance of large language models (LLMs) in clinical contexts. Unlike existing benchmarks that focus on multiple-choice question answering, MedS-Bench spans 11 high-level clinical tasks, including clinical report summarization, treatment recommendations, diagnosis, named entity recognition, and medical concept explanation, among others. We evaluated six leading LLMs, e.g., MEDITRON, Mistral, InternLM 2, Llama 3, GPT-4, and Claude-3.5 using few-shot prompting, and found that even the most sophisticated models struggle with these complex tasks. To address these limitations, we developed MedS-Ins, a large-scale instruction tuning dataset for medicine. MedS-Ins comprises 58 medically oriented language corpora, totaling 13.5 million samples across 122 tasks. To demonstrate the dataset's utility, we conducted a proof-of-concept experiment by performing instruction tuning on a lightweight, open-source medical language model. The resulting model, MMedIns-Llama 3, significantly outperformed existing models across nearly all clinical tasks. To promote further advancements in the application of LLMs to clinical challenges, we have made the MedS-Ins dataset fully accessible and invite the research community to contribute to its expansion.Additionally, we have launched a dynamic leaderboard for MedS-Bench, which we plan to regularly update the test set to track progress and enhance the adaptation of general LLMs to the medical domain. Leaderboard: https://henrychur.github.io/MedS-Bench/. Github: https://github.com/MAGIC-AI4Med/MedS-Ins.
Abstract:In this paper, we aim to develop an open-source, multilingual language model for medicine, that the benefits a wider, linguistically diverse audience from different regions. In general, we present the contribution from the following aspects: first, for multilingual medical-specific adaptation, we construct a new multilingual medical corpus, that contains approximately 25.5B tokens encompassing 6 main languages, termed as MMedC, that enables auto-regressive training for existing general LLMs. second, to monitor the development of multilingual LLMs in medicine, we propose a new multilingual medical multi-choice question-answering benchmark with rationale, termed as MMedBench; third, we have assessed a number of popular, opensource large language models (LLMs) on our benchmark, along with those further auto-regressive trained on MMedC, as a result, our final model, termed as MMedLM 2, with only 7B parameters, achieves superior performance compared to all other open-source models, even rivaling GPT-4 on MMedBench. We will make the resources publicly available, including code, model weights, and datasets.