{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/m-qalm-a-benchmark-to-assess-clinical-reading","title":"M-QALM: A Benchmark to Assess Clinical Reading Comprehension and Knowledge Recall in Large Language Models via Question Answering","arxiv_id":"2406.03699","date":"2024-06-06","proceeding":null,"authors":["Anand Subramanian","Viktor Schlegel","Abhinav Ramesh Kashyap","Thanh-Tung Nguyen","Vijay Prakash Dwivedi","Stefan Winkler"],"abstract":"There is vivid research on adapting Large Language Models (LLMs) to perform a variety of tasks in high-stakes domains such as healthcare. Despite their popularity, there is a lack of understanding of the extent and contributing factors that allow LLMs to recall relevant knowledge and combine it with presented information in the clinical and biomedical domain: a fundamental pre-requisite for success on down-stream tasks. Addressing this gap, we use Multiple Choice and Abstractive Question Answering to conduct a large-scale empirical study on 22 datasets in three generalist and three specialist biomedical sub-domains. Our multifaceted analysis of the performance of 15 LLMs, further broken down by sub-domain, source of knowledge and model architecture, uncovers success factors such as instruction tuning that lead to improved recall and comprehension. We further show that while recently proposed domain-adapted models may lack adequate knowledge, directly fine-tuning on our collected medical knowledge datasets shows encouraging results, even generalising to unseen specialist sub-domains. We complement the quantitative results with a skill-oriented manual error analysis, which reveals a significant gap between the models' capabilities to simply recall necessary knowledge and to integrate it with the presented context. To foster research and collaboration in this field we share M-QALM, our resources, standardised methodology, and evaluation results, with the research community to facilitate further advancements in clinical knowledge representation learning within language models.","url_abs":"https://arxiv.org/abs/2406.03699v1","url_pdf":"https://arxiv.org/pdf/2406.03699v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"m-qalm-a-benchmark-to-assess-clinical-reading","repo_url":"https://github.com/anand-subu/m-qalm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"clinical-knowledge","task_name":"Clinical Knowledge"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":null,"task_name":"abstractive question answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}