Saved in:
Bibliographic Details
Main Authors: Feng, Xiang, Jiang, Wentao, Wang, Zengmao, Luo, Yong, Xu, Pingbo, Yu, Baosheng, Jin, Hua, Zhang, Jing
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.02404
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914362355089408
author Feng, Xiang
Jiang, Wentao
Wang, Zengmao
Luo, Yong
Xu, Pingbo
Yu, Baosheng
Jin, Hua
Zhang, Jing
author_facet Feng, Xiang
Jiang, Wentao
Wang, Zengmao
Luo, Yong
Xu, Pingbo
Yu, Baosheng
Jin, Hua
Zhang, Jing
contents The application of large language models (LLMs) in the medical field has garnered significant attention, yet their reasoning capabilities in more specialized domains like anesthesiology remain underexplored. To bridge this gap, we introduce AnesSuite, the first comprehensive dataset suite specifically designed for anesthesiology reasoning in LLMs. The suite features AnesBench, an evaluation benchmark tailored to assess anesthesiology-related reasoning across three levels: factual retrieval (System 1), hybrid reasoning (System 1.x), and complex decision-making (System 2). Alongside this benchmark, the suite includes three training datasets that provide an infrastructure for continued pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning with verifiable rewards (RLVR). Leveraging this suite, we develop Morpheus, the first baseline model collection for anesthesiology reasoning. Despite undergoing limited training with SFT and group relative policy optimization (GRPO), Morpheus not only achieves substantial improvements in anesthesiology that rival larger-scale models, but also demonstrates enhanced reasoning capabilities across general medical and broad-domain benchmarks. Furthermore, through comprehensive evaluations and experiments, we analyze the key factors influencing anesthesiology reasoning performance, including model characteristics, training strategies and training data. Both AnesSuite and Morpheus will be open-sourced at https://github.com/MiliLab/AnesSuite.
format Preprint
id arxiv_https___arxiv_org_abs_2504_02404
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AnesSuite: A Comprehensive Benchmark and Dataset Suite for Anesthesiology Reasoning in LLMs
Feng, Xiang
Jiang, Wentao
Wang, Zengmao
Luo, Yong
Xu, Pingbo
Yu, Baosheng
Jin, Hua
Zhang, Jing
Computation and Language
The application of large language models (LLMs) in the medical field has garnered significant attention, yet their reasoning capabilities in more specialized domains like anesthesiology remain underexplored. To bridge this gap, we introduce AnesSuite, the first comprehensive dataset suite specifically designed for anesthesiology reasoning in LLMs. The suite features AnesBench, an evaluation benchmark tailored to assess anesthesiology-related reasoning across three levels: factual retrieval (System 1), hybrid reasoning (System 1.x), and complex decision-making (System 2). Alongside this benchmark, the suite includes three training datasets that provide an infrastructure for continued pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning with verifiable rewards (RLVR). Leveraging this suite, we develop Morpheus, the first baseline model collection for anesthesiology reasoning. Despite undergoing limited training with SFT and group relative policy optimization (GRPO), Morpheus not only achieves substantial improvements in anesthesiology that rival larger-scale models, but also demonstrates enhanced reasoning capabilities across general medical and broad-domain benchmarks. Furthermore, through comprehensive evaluations and experiments, we analyze the key factors influencing anesthesiology reasoning performance, including model characteristics, training strategies and training data. Both AnesSuite and Morpheus will be open-sourced at https://github.com/MiliLab/AnesSuite.
title AnesSuite: A Comprehensive Benchmark and Dataset Suite for Anesthesiology Reasoning in LLMs
topic Computation and Language
url https://arxiv.org/abs/2504.02404