Saved in:
Bibliographic Details
Main Authors: Adly, Ahmed M., Samy, Mostafa, Fawzy, Amr
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.21594
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916812091817984
author Adly, Ahmed M.
Samy, Mostafa
Fawzy, Amr
author_facet Adly, Ahmed M.
Samy, Mostafa
Fawzy, Amr
contents We present Gazal-R1, a 32-billion-parameter language model that achieves state-of-the-art performance in medical reasoning while providing transparent, step-by-step explanations for clinical decision-making. Built upon Qwen3 32B, our model demonstrates that strategic training can enable mid-sized models to outperform significantly larger counterparts in specialized domains. We developed a novel two-stage training pipeline: first, supervised fine-tuning on a carefully curated dataset of 107,033 synthetic medical reasoning examples that teaches structured clinical thinking, enhanced by advanced parameter-efficient techniques including Weight-Decomposed Low-Rank Adaptation (DoRA) and Rank-Stabilized LoRA (rsLoRA); second, reinforcement learning using Group Relative Policy Optimization (GRPO) with a sophisticated multi-component reward system that refines accuracy, format adherence, and reasoning quality. Gazal-R1 achieves exceptional performance across medical benchmarks, scoring 87.1% on MedQA, 81.6% on MMLU Pro (Medical), and 79.6% on PubMedQA, surpassing models up to 12x larger. Beyond its strong empirical results, this work provides detailed insights into the challenges of training reasoning-capable models in specialized domains, including issues with reward hacking, training instability, and the fundamental tension between factual recall and detailed reasoning. Our methodology offers a reproducible framework for developing high-capability, domain-specific language models that balance performance, efficiency, and explainability.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21594
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Gazal-R1: Achieving State-of-the-Art Medical Reasoning with Parameter-Efficient Two-Stage Training
Adly, Ahmed M.
Samy, Mostafa
Fawzy, Amr
Computation and Language
We present Gazal-R1, a 32-billion-parameter language model that achieves state-of-the-art performance in medical reasoning while providing transparent, step-by-step explanations for clinical decision-making. Built upon Qwen3 32B, our model demonstrates that strategic training can enable mid-sized models to outperform significantly larger counterparts in specialized domains. We developed a novel two-stage training pipeline: first, supervised fine-tuning on a carefully curated dataset of 107,033 synthetic medical reasoning examples that teaches structured clinical thinking, enhanced by advanced parameter-efficient techniques including Weight-Decomposed Low-Rank Adaptation (DoRA) and Rank-Stabilized LoRA (rsLoRA); second, reinforcement learning using Group Relative Policy Optimization (GRPO) with a sophisticated multi-component reward system that refines accuracy, format adherence, and reasoning quality. Gazal-R1 achieves exceptional performance across medical benchmarks, scoring 87.1% on MedQA, 81.6% on MMLU Pro (Medical), and 79.6% on PubMedQA, surpassing models up to 12x larger. Beyond its strong empirical results, this work provides detailed insights into the challenges of training reasoning-capable models in specialized domains, including issues with reward hacking, training instability, and the fundamental tension between factual recall and detailed reasoning. Our methodology offers a reproducible framework for developing high-capability, domain-specific language models that balance performance, efficiency, and explainability.
title Gazal-R1: Achieving State-of-the-Art Medical Reasoning with Parameter-Efficient Two-Stage Training
topic Computation and Language
url https://arxiv.org/abs/2506.21594