Daily Papers

Visual grounding is essential for precise perception and reasoning in multimodal large language models (MLLMs), especially in medical imaging domains. While existing medical visual grounding benchmarks primarily focus on single-image scenarios, real-world clinical applications often involve sequential images, where accurate lesion localization across different modalities and temporal tracking of disease progression (e.g., pre- vs. post-treatment comparison) require fine-grained cross-image semantic alignment and context-aware reasoning. To remedy the underrepresentation of image sequences in existing medical visual grounding benchmarks, we propose MedSG-Bench, the first benchmark tailored for Medical Image Sequences Grounding. It comprises eight VQA-style tasks, formulated into two paradigms of the grounding tasks, including 1) Image Difference Grounding, which focuses on detecting change regions across images, and 2) Image Consistency Grounding, which emphasizes detection of consistent or shared semantics across sequential images. MedSG-Bench covers 76 public datasets, 10 medical imaging modalities, and a wide spectrum of anatomical structures and diseases, totaling 9,630 question-answer pairs. We benchmark both general-purpose MLLMs (e.g., Qwen2.5-VL) and medical-domain specialized MLLMs (e.g., HuatuoGPT-vision), observing that even the advanced models exhibit substantial limitations in medical sequential grounding tasks. To advance this field, we construct MedSG-188K, a large-scale instruction-tuning dataset tailored for sequential visual grounding, and further develop MedSeq-Grounder, an MLLM designed to facilitate future research on fine-grained understanding across medical sequential images. The benchmark, dataset, and model are available at https://huggingface.co/MedSG-Bench

Clinicians rarely localize a finding from one image alone. They compare current and prior scans, follow structures across slices, and match regions across views or modalities. Yet vision-language models for sequential medical grounding usually learn only from bounding boxes. Boxes show where the target is, but they do not explain why that region in that image answers the question. We study whether explicit, image-grounded reasoning can improve localization, and which tasks benefit from it. We introduce method, whose core is MedChain, a corpus of 182,573 filtered rationales spanning eight sequential grounding tasks and ten imaging modalities. A medical VLM (FlemingVL-38B) first drafts a caption-like rationale, and a multimodal refiner (Qwen3.5-397B-A17B) then re-examines the images, question and annotated box to write a box-conditioned explanation with explicit cross-image reasoning. We fine-tune Qwen3.5 on these rationales with deliberative chain-of-thought supervision (dCoT-SFT). Across 4B, 9B, and 27B models, dCoT-SFT sets a new state of the art on MedSG-Bench. The 27B model reaches 77.24 mIoU and 85.20 Acc@0.5, improving over the strongest prior model by 4.69 and 5.49 points. In a paired comparison using fixed 4B checkpoints, dCoT-SFT improves over answer-only SFT by 3.56 mIoU (95% CI 3.13--4.00). The gains mainly come from change detection and object tracking, while performance drops on three appearance-matching tasks. Replacing a model's own rationale with a rationale from another task reduces mIoU by 12.2 points, showing that localization depends strongly on the reasoning context. Finally, adding GRPO with an IoU reward after dCoT-SFT gives only small and task-dependent gains, which we analyze through controlled multi-seed development experiments.

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.

The proliferation of Large Language Models (LLMs) presents transformative potential for healthcare, yet practical deployment is hindered by the absence of frameworks that assess real-world clinical utility. Existing benchmarks test static knowledge, failing to capture the dynamic, application-oriented capabilities required in clinical practice. To bridge this gap, we introduce a Medical LLM Benchmark MLB, a comprehensive benchmark evaluating LLMs on both foundational knowledge and scenario-based reasoning. MLB is structured around five core dimensions: Medical Knowledge (MedKQA), Safety and Ethics (MedSE), Medical Record Understanding (MedRU), Smart Services (SmartServ), and Smart Healthcare (SmartCare). The benchmark integrates 22 datasets (17 newly curated) from diverse Chinese clinical sources, covering 64 clinical specialties. Its design features a rigorous curation pipeline involving 300 licensed physicians. Besides, we provide a scalable evaluation methodology, centered on a specialized judge model trained via Supervised Fine-Tuning (SFT) on expert annotations. Our comprehensive evaluation of 10 leading models reveals a critical translational gap: while the top-ranked model, Kimi-K2-Instruct (77.3% accuracy overall), excels in structured tasks like information extraction (87.8% accuracy in MedRU), performance plummets in patient-facing scenarios (61.3% in SmartServ). Moreover, the exceptional safety score (90.6% in MedSE) of the much smaller Baichuan-M2-32B highlights that targeted training is equally critical. Our specialized judge model, trained via SFT on a 19k expert-annotated medical dataset, achieves 92.1% accuracy, an F1-score of 94.37%, and a Cohen's Kappa of 81.3% for human-AI consistency, validating a reproducible and expert-aligned evaluation protocol. MLB thus provides a rigorous framework to guide the development of clinically viable LLMs.

Developing conversational agents to interact with patients and provide primary clinical advice has attracted increasing attention due to its huge application potential, especially in the time of COVID-19 Pandemic. However, the training of end-to-end neural-based medical dialogue system is restricted by an insufficient quantity of medical dialogue corpus. In this work, we make the first attempt to build and release a large-scale high-quality Medical Dialogue dataset related to 12 types of common Gastrointestinal diseases named MedDG, with more than 17K conversations collected from the online health consultation community. Five different categories of entities, including diseases, symptoms, attributes, tests, and medicines, are annotated in each conversation of MedDG as additional labels. To push forward the future research on building expert-sensitive medical dialogue system, we proposes two kinds of medical dialogue tasks based on MedDG dataset. One is the next entity prediction and the other is the doctor response generation. To acquire a clear comprehension on these two medical dialogue tasks, we implement several state-of-the-art benchmarks, as well as design two dialogue models with a further consideration on the predicted entities. Experimental results show that the pre-train language models and other baselines struggle on both tasks with poor performance in our dataset, and the response quality can be enhanced with the help of auxiliary entity information. From human evaluation, the simple retrieval model outperforms several state-of-the-art generative models, indicating that there still remains a large room for improvement on generating medically meaningful responses.