paper-with-me

Papers

ClinicalGPT-R1: Pushing reasoning capability of generalist disease diagnosis with large language model

2025-04-13 · Wuyang Lan, Wenzheng Wang, Changwei Ji, Guoxing Yang, Yongbo Zhang, Xiaohong Liu, Song Wu, Guangyu Wang

Recent advances in reasoning with large language models (LLMs)has shown remarkable reasoning capabilities in domains such as mathematics and coding, yet their application to clinical diagnosis remains underexplored. Here, we introduce ClinicalGPT-R1, a reasoning enhanced generalist large language model for disease diagnosis. Trained on a dataset of 20,000 real-world clinical records, ClinicalGPT-R1 leverages diverse training strategies to enhance diagnostic reasoning. To benchmark performance, we curated MedBench-Hard, a challenging dataset spanning seven major medical specialties and representative diseases. Experimental results demonstrate that ClinicalGPT-R1 outperforms GPT-4o in Chinese diagnostic tasks and achieves comparable performance to GPT-4 in English settings. This comparative study effectively validates the superior performance of ClinicalGPT-R1 in disease diagnosis tasks. Resources are available at https://github.com/medfound/medfound.

📄 PDF Abstract BibTeX arXiv:2504.09421

Code (1)

medfound/medfound 공식 구현 pytorch

Tasks

DiagnosticLanguage ModelingLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Position-Wise Feed-Forward Layer 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Residual Connection 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

ClinicalGPT: Large Language Models Finetuned with Diverse Medical Data and Comprehensive Evaluation

2023-06-16 · Guangyu Wang, Guoxing Yang, Zongxin Du, Longjun Fan 외

Large language models have exhibited exceptional performance on various Natural Language Processing (NLP) tasks, leveraging techniques such as the pre-training, and instruction fine-tuning. Despite these advances, their …

DiagnosticLanguage ModelingLanguage ModellingQuestion Answering

Super-Generalist: Towards Comprehensive and Accurate Medical Image Understanding via Generalist-Specialist Synergy

2026-07-10 · Shaoteng Zhang, Weiwei Cao, Wanxing Chang, Yutong Xie 외 arxiv

Medical images require comprehensive and accurate interpretation to support the diagnosis of diverse clincial conditions. Recent vision-language generalist models offer broad task coverage and promising zero-shot capabil…

EVLF-FM: Explainable Vision Language Foundation Model for Medicine

2025-09-29 · Yang Bai, Haoran Cheng, Yang Zhou, Jun Zhou 외 arxiv

Despite the promise of foundation models in medical AI, current systems remain limited - they are modality-specific and lack transparent reasoning processes, hindering clinical adoption. To address this gap, we present E…

Visual Question AnsweringVisual Grounding

Large language models require a new form of oversight: capability-based monitoring

2025-11-05 · Katherine C. Kellogg, Bingyang Ye, Yifan Hu, Guergana K. Savova 외 arxiv

The rapid adoption of large language models (LLMs) in healthcare has been accompanied by scrutiny of their oversight. Existing monitoring approaches, inherited from traditional machine learning (ML), are task-based and f…

Harnessing Generalist Agents for Contextualized Time Series

2026-06-03 · Zihao Li, Kaifeng Jin, Yuanchen Bei, Jiaru Zou 외 arxiv

Time series are often embedded in rich contexts that are essential for holistic modeling. Moreover, real-world practitioners often require end-to-end workflows for analyzing temporal dynamics, where widely studied tasks …