Medical Reasoning

Follow this topic Ask about this topic

Medical reasoning asks whether AI can move beyond recalling medical facts to make sound decisions from clinical evidence, patient-specific conditions, images, signals, and longitudinal records. Common approaches include retrieval-augmented generation, structured reasoning and knowledge graphs, specialist-agent collaboration, and fine-tuning with step-level rewards or clinician-designed rubrics. Benchmarks increasingly test multi-step inference, image and ECG interpretation, rare cases, medication safety, and whether conclusions change appropriately when patient details change. A central challenge is that correct answers and persuasive explanations do not guarantee faithful reasoning or reliable clinical decisions, so evaluation must examine evidence use, intermediate steps, and performance on authentic cases.

Latest papers

31 papers4 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Multilingual Medical Reasoning for Question Answering with Large Language Models
Dec 5, 2025Pietro Ferrazzi, Aitor Soroa, Rodrigo AgerriKnowledge Augmentation for Language Models Healthcare
Fondazione Bruno Kessler, Trento, Italy · HiTZ Center - Ixa, University of the Basque Country EHU, Spain

Dec 5, 2025J/K move · Enter open · S save

Multilingual Medical Reasoning for Question Answering with Large Language Models

Pietro Ferrazzi, Aitor Soroa, Rodrigo Agerri

Fondazione Bruno Kessler, Trento, Italy · HiTZ Center - Ixa, University of the Basque Country EHU, Spain

Knowledge Augmentation for Language Models Healthcare Medical QA Multilingual QA Medical Reasoning Medical LLMs

Open paper AskPDF arXiv

Large Language Models (LLMs) with reasoning capabilities have recently demonstrated strong potential in medical Question Answering (QA). Existing approaches are largely English-focused and primarily rely on distillation from general-purpose LLMs, raising concerns about the reliability of their medical knowledge. In this work, we present a method to generate multilingual reasoning traces based on medical knowledge extracted from Wikipedia. We produce 500k traces in English, Italian, and Spanish, using a retrieval-augmented generation approach over medical information from Wikipedia. The traces are generated to solve medical questions drawn from MedQA and MedMCQA, which we extend to Italian and Spanish. We test our pipeline in both in-domain and out-of-domain settings across Medical QA benchmarks, and demonstrate that our reasoning traces improve performance both when utilized via in-context learning (few-shot) and supervised fine-tuning, yielding state-of-the-art results among 8B-parameter LLMs. We believe that these resources can support the development of more transparent clinical decision-support tools in multilingual settings. We release the full suite of resources: reasoning traces, translated QA datasets, Medical-Wikipedia, and fine-tuned models.