{"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/medmobile-a-mobile-sized-language-model-with","title":"MedMobile: A mobile-sized language model with expert-level clinical capabilities","arxiv_id":"2410.09019","date":"2024-10-11","proceeding":null,"authors":["Krithik Vishwanath","Jaden Stryker","Anton Alaykin","Daniel Alexander Alber","Eric Karl Oermann"],"abstract":"Language models (LMs) have demonstrated expert-level reasoning and recall abilities in medicine. However, computational costs and privacy concerns are mounting barriers to wide-scale implementation. We introduce a parsimonious adaptation of phi-3-mini, MedMobile, a 3.8 billion parameter LM capable of running on a mobile device, for medical applications. We demonstrate that MedMobile scores 75.7% on the MedQA (USMLE), surpassing the passing mark for physicians (~60%), and approaching the scores of models 100 times its size. We subsequently perform a careful set of ablations, and demonstrate that chain of thought, ensembling, and fine-tuning lead to the greatest performance gains, while unexpectedly retrieval augmented generation fails to demonstrate significant improvements","url_abs":"https://arxiv.org/abs/2410.09019v1","url_pdf":"https://arxiv.org/pdf/2410.09019v1.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":"medmobile-a-mobile-sized-language-model-with","repo_url":"https://github.com/nyuolab/MedMobile","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":null,"task_name":"MedQA"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"retrieval-augmented-generation","task_name":"Retrieval-augmented Generation"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-medmcqa-dev","task":"Question Answering","dataset":"MedMCQA Dev","model":"MedMobile (3.8B)","rank_in_archive_order":1,"of":1,"metrics":{"Accuarcy":"63.2"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-medqa-usmle","task":"Question Answering","dataset":"MedQA","model":"MedMobile (3.8B)","rank_in_archive_order":6,"of":27,"metrics":{"Accuracy":"75.7"},"uses_additional_data":true}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}