Grounded Multilingual Medical Reasoning for Question Answering with Large Language Models

• URL: http://arxiv.org/abs/2512.05658v1
• Date: Fri, 05 Dec 2025 12:05:46 GMT
• Title: Grounded Multilingual Medical Reasoning for Question Answering with Large Language Models
• Authors: Pietro Ferrazzi, Aitor Soroa, Rodrigo Agerri,
• Abstract summary: We present a method to generate multilingual reasoning traces grounded in factual medical knowledge.<n>We produce 500k traces in English, Italian, and Spanish, using a retrievalaugmented generation approach over medical information from Wikipedia.
• Score: 15.135129023906138
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: 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 grounded in factual medical knowledge. We produce 500k traces in English, Italian, and Spanish, using a retrievalaugmented 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 outof-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 safer, 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.

Related papers

• MedQARo: A Large-Scale Benchmark for Medical Question Answering in Romanian [50.767415194856135]
  We introduce MedQARo, the first large-scale medical QA benchmark in Romanian.<n>We construct a high-quality and large-scale dataset comprising 102,646 QA pairs related to cancer patients.
  arXiv  Detail & Related papers  (2025-08-22T13:48:37Z)
• MKG-Rank: Enhancing Large Language Models with Knowledge Graph for Multilingual Medical Question Answering [32.60615474034456]
  We propose Multilingual Knowledge Graph-based Retrieval Ranking (MKG-Rank) for multilingual medical question answering.<n>Our framework integrates comprehensive English-centric medical knowledge graphs into LLM reasoning at a low cost.<n>Extensive evaluations on multilingual medical QA benchmarks across Chinese, Japanese, Korean, and Swahili demonstrate that MKG-Rank consistently outperforms zero-shot LLMs.
  arXiv  Detail & Related papers  (2025-03-20T13:25:03Z)
• Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models [62.91524967852552]
  Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora.<n>But can these models relate corresponding concepts across languages, i.e., be crosslingual?<n>This study evaluates state-of-the-art LLMs on inherently crosslingual tasks.
  arXiv  Detail & Related papers  (2024-06-23T15:15:17Z)
• MedExpQA: Multilingual Benchmarking of Large Language Models for Medical Question Answering [8.110978727364397]
  Large Language Models (LLMs) have the potential of facilitating the development of Artificial Intelligence technology. This paper presents MedExpQA, the first multilingual benchmark based on medical exams to evaluate LLMs in Medical Question Answering.
  arXiv  Detail & Related papers  (2024-04-08T15:03:57Z)
• Towards Building Multilingual Language Model for Medicine [54.1382395897071]
  We construct a multilingual medical corpus, containing approximately 25.5B tokens encompassing 6 main languages. We propose a multilingual medical multi-choice question-answering benchmark with rationale, termed as MMedBench. Our final model, MMed-Llama 3, with only 8B parameters, achieves superior performance compared to all other open-source models on both MMedBench and English benchmarks.
  arXiv  Detail & Related papers  (2024-02-21T17:47:20Z)
• Explanatory Argument Extraction of Correct Answers in Resident Medical Exams [5.399800035598185]
  We present a new dataset which includes not only explanatory arguments for the correct answer, but also arguments to reason why the incorrect answers are not correct. This new benchmark allows us to setup a novel extractive task which consists of identifying the explanation of the correct answer written by medical doctors.
  arXiv  Detail & Related papers  (2023-12-01T13:22:35Z)
• ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferences [51.66185471742271]
  We propose ChiMed-GPT, a benchmark LLM designed explicitly for Chinese medical domain. ChiMed-GPT undergoes a comprehensive training regime with pre-training, SFT, and RLHF. We analyze possible biases through prompting ChiMed-GPT to perform attitude scales regarding discrimination of patients.
  arXiv  Detail & Related papers  (2023-11-10T12:25:32Z)
• Evaluating and Modeling Attribution for Cross-Lingual Question Answering [80.4807682093432]
  This work is the first to study attribution for cross-lingual question answering. We collect data in 5 languages to assess the attribution level of a state-of-the-art cross-lingual QA system. We find that a substantial portion of the answers is not attributable to any retrieved passages.
  arXiv  Detail & Related papers  (2023-05-23T17:57:46Z)
• PMC-LLaMA: Towards Building Open-source Language Models for Medicine [62.39105735933138]
  Large Language Models (LLMs) have showcased remarkable capabilities in natural language understanding. LLMs struggle in domains that require precision, such as medical applications, due to their lack of domain-specific knowledge. We describe the procedure for building a powerful, open-source language model specifically designed for medicine applications, termed as PMC-LLaMA.
  arXiv  Detail & Related papers  (2023-04-27T18:29:05Z)
• Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Models [42.360431316298204]
  We focus on open-ended VQA and motivated by the recent advances in language models consider it as a generative task. To properly communicate the medical images to the language model, we develop a network that maps the extracted visual features to a set of learnable tokens. We evaluate our approach on the prime medical VQA benchmarks, namely, Slake, OVQA and PathVQA.
  arXiv  Detail & Related papers  (2023-03-10T15:17:22Z)
• Learning Domain-Specialised Representations for Cross-Lingual Biomedical Entity Linking [66.76141128555099]
  We propose a novel cross-lingual biomedical entity linking task (XL-BEL) We first investigate the ability of standard knowledge-agnostic as well as knowledge-enhanced monolingual and multilingual LMs beyond the standard monolingual English BEL task. We then address the challenge of transferring domain-specific knowledge in resource-rich languages to resource-poor ones.
  arXiv  Detail & Related papers  (2021-05-30T00:50:00Z)
• Knowledge-Empowered Representation Learning for Chinese Medical Reading Comprehension: Task, Model and Resources [36.960318276653986]
  We introduce a multi-target MRC task for the medical domain, whose goal is to predict answers to medical questions and the corresponding support sentences simultaneously. We propose the Chinese medical BERT model for the task (CMedBERT), which fuses medical knowledge into pre-trained language models. Experiments show that CMedBERT consistently outperforms strong baselines by fusing context-aware and knowledge-aware token representations.
  arXiv  Detail & Related papers  (2020-08-24T11:23:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.