{"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/process-supervised-reward-models-for-clinical","title":"Process-Supervised Reward Models for Clinical Note Generation: A Scalable Approach Guided by Domain Expertise","arxiv_id":"2412.12583","date":"2024-12-17","proceeding":null,"authors":["Hanyin Wang","Qiping Xu","Bolun Liu","Guleid Hussein","Hariprasad Korsapati","Mohamad El Labban","Kingsley Iheasirim","Mohamed Hassan","Gokhan Anil","Brian Bartlett","Jimeng Sun"],"abstract":"Process-supervised reward models (PRMs), which verify large language model (LLM) outputs step-by-step, have achieved significant success in mathematical and coding problems. However, their application to other domains remains largely unexplored. In this work, we train a PRM to provide step-level reward signals for clinical notes generated by LLMs from patient-doctor dialogues. Guided by real-world clinician expertise, we carefully designed step definitions for clinical notes and utilized Gemini-Pro 1.5 to automatically generate process supervision data at scale. Our proposed PRM, trained on the LLaMA-3.1 8B instruct model, demonstrated superior performance compared to Gemini-Pro 1.5 and an outcome-supervised reward model (ORM) across two key evaluations: (1) the accuracy of selecting gold-reference samples from error-containing samples, achieving 98.8% (versus 61.3% for ORM and 93.8% for Gemini-Pro 1.5), and (2) the accuracy of selecting physician-preferred notes, achieving 56.2% (compared to 51.2% for ORM and 50.0% for Gemini-Pro 1.5). Additionally, we conducted ablation studies to determine optimal loss functions and data selection strategies, along with physician reader studies to explore predictors of downstream Best-of-N performance. Our promising results suggest the potential of PRMs to extend beyond the clinical domain, offering a scalable and effective solution for diverse generative tasks.","url_abs":"https://arxiv.org/abs/2412.12583v1","url_pdf":"https://arxiv.org/pdf/2412.12583v1.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":"process-supervised-reward-models-for-clinical","repo_url":"https://github.com/hanyin88/prm-clinic","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2412.12583","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}