Sep 2026· Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing· Vol abs/2609.24480· 0 citations· 22 references
Computer Science
TL;DR
The results show that targeted synthetic datasets and rubric-based training can systematically improve both diagnostic and interactive clinical reasoning in medical LLMs.
Abstract
Deploying Large Language Models (LLMs) in healthcare requires robust performance across two complementary dimensions - diagnostic reasoning: the convergent, evidence-driven task of inferring a patient's condition from clinical data to produce a diagnosis, and clinical healthcare reasoning: the broader, navigational judgment required to communicate, plan, and adapt across multi-turn clinical interactions where a single correct answer may not exist. Recent benchmarks such as HealthBench and MedXpertQA reveal persistent weaknesses in both areas, exposing failures in complex diagnostic scenarios and limitations in contextual, patient-centered dialogue. We introduce a sequential training framework that targets these facets using synthetic data and rubric-based reinforcement learning. First, we improve diagnostic reasoning using MedBullets-derived questions with rule- and rubric-guided Reinforcement Learning (RL). We then shift to clinical reasoning by generating 5.3k synthetic multi-turn scenarios, each paired with multi-dimensional rubrics to comprehensively assess the response. This approach yields over 10% improvement on MedXpertQA, and our 30B model achieves 50.1% accuracy on HealthBench-Hard, surpassing proprietary baselines including GPT-5 (thinking). Our results show that targeted synthetic datasets and rubric-based training can systematically improve both diagnostic and interactive clinical reasoning in medical LLMs.
This paper introduces MedRouter, an agentic system that uses an embedding-based multi-label router to select and query specialist LLMs, then passes their responses to a generator to produce the final answer, and proposes SCALE (Specialist Competence-Aware Learning), a two-stage training framework.
Lang Cao, Bing-Hang Lu, Yu-Hao Shen et al.· 0 citations
This paradigm shift from misuse to misclassification is not semantic: it offers educators a clear perspective on what to look for, what to assess, and what to intervene on.
Fendi Tsim, A. Gutoreva, A. Weiss et al.· 0 citations
Medical language models can produce correct diagnoses despite incomplete investigations and unsupported reasoning. To support long-horizon, evidence-grounded diagnosis, we introduce \textbf{TrustMed-RL}. Built from PubMed rare-disease cases and over 24,000 manually annotated image panels, it integrates interviews, exam...
Wen-Xin Zhan, Yi-Zheng Jiao, Hai-Feng Song et al.· 0 citations
This review explores the transformative impact of Large Language Models on medical question-answering robots and addresses critical challenges faced by LLM-driven systems, such as limited interpretability, restricted applicability across medical domains, and serious concerns about patient privacy.
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.