Grant to Improve Factual Correctness in Large Language Models in Health Care

Grant to Improve Factual Correctness in Large Language Models in Health Care is sponsored by National Institutes of Health (NIH) - National Library of Medicine. This project addresses critical issues of factual inaccuracy and unfaithful reasoning in Large Language Models (LLMs) for biomedicine and health care.

NIH Awards $1. 5 Million Grant to Improve Factual Correctness in Large Language Models in Health Care | Yale School of Medicine Your browser is antiquated and no longer supported on this website. Please update your browser or switch to Chrome, Firefox or Safari.

You can update your IE here: https://support. microsoft.

com/en-us/help/17621/internet-explorer-downloads Leadership, Administration & Governance YSM Board of Permanent Officers Appointments & Promotions Committees Ad Hoc Committees and Working Groups Professionalism Reporting Data Diversity Engagement Surveys State of the School Archive Faculty Climate Survey: YSM Results Mission Statement & Process Yale Biomedical Imaging Institute: Advancing the Understanding of Health & Guiding Treatment Stephen & Denise Adams Center for Parkinson’s Disease Research Integrating Systems Immunology, Engineering, and AI to Monitor, Predict, and Improve Human Health Dept.

Vice Chairs & Advocates Director of Faculty Development and Collaborative Excellence For Students, Trainees, & Postdocs YSM Science Fellows Program Frequently Asked Questions Program for Art in Public Spaces Aperture: Women in Medicine Mindful: Mental Health Through Art Health Services, Policy, and Outcomes Clinical Informatics & Data Science Courses for CIDS, CI, HPO, and MedEd Programs Online Courses for Medical AI Program Visiting Student Programs Special Programs & Student Opportunities Residency & Fellowship Programs Office of the Deputy Dean Educational Technology & Innovation Academic & Professional Development Committee Procedural Info (Login Required) Faculty Affairs Department Teams Recent Appointments & Promotions Faculty Tracks, Ranks, & Positions Clinician Educator-Scholar Track Clinician-Scientist Track Appointments, Promotions, and Reappointments Leaves, Term Extensions, Part-Time, & Retirement Timeline for A&P Processes Faculty Search Recommended Practices Faculty Affairs Staff Pages Leadership & Development Seminars Incoming Faculty Orientation Staff Tools (Login Required) Past YSM Award Recipients International Award Recipients Fostering a Shared Vision of Professionalism Addressing Professionalism Concerns Consultation Support for Chairs & Section Chiefs Policies & Codes of Conduct Physician/Scientist Development Physician-Scientist Development Awards Faculty Facing Caregiving Need Physician-Scientist Resident & Fellow Research Award Fund for Physician-Scientist Mentorship Establishing a Thriving Research Program Join Our Voluntary Faculty Health & Wellness Resources Research by Global Location Research Cores & Services Resources for Investigators Program for the Promotion of Interdisciplinary Team Science (POINTS) Steering Committee on Community-Partnered Research Health Equity Research Methods Bootcamp Community Health Equity Accelerator Community Research Innovation Summit Community Research Fellows Program OHER Awards for Yale Research Excellence Health Equity Community Visiting Scholars Health Equity Visiting Professors Community Research Consultants Network Community Engagement Research Studios The National Institutes of Health (NIH) has awarded $1.

5 million to a project that addresses the critical issues of factual inaccuracy and unfaithful reasoning in Large Language Models (LLMs) for biomedicine and health care. The project, led by principal investigator Qingyu Chen, PhD , is funded by the National Library of Medicine under grant number 1R01LM014604-01, with a project period extending from August 2024 to July 2028.

As AI continues to revolutionize health care, ensuring the reliability of its outputs is crucial. Improving factual accuracy and reasoning in domain-specific LLMs is crucial, as it will benefit a range of downstream applications in the biomedical and health domains. LLMs hold transformative potential across numerous fields, including health care.

However, their susceptibility to generating inaccurate or misleading information poses significant risks, especially in medical contexts, where misinformation could result in misdiagnosis or improper treatment. Dr. Chen’s project aims to address these concerns by developing a robust framework that improves the factual accuracy and reasoning of LLM-generated responses in biomedical applications.

The research initiative systematically tackles the challenges LLMs face in generating reliable outputs for biomedicine. Key strategies include: Establishing a Biomedical Digital Resource Framework: This framework will provide LLMs with up-to-date biomedical knowledge, enhancing their ability to deliver trustworthy information.

Developing New Natural Language Processing Techniques: These techniques will facilitate automatic fact-checking to improve the correctness of LLM responses. Implementing a Feedback-Guided Paradigm: This system will enable LLMs to identify and correct errors, refining their outputs over time.

The project involves an interdisciplinary team from Yale including Hua Xu, PhD ; Andrew Taylor, MD, MHS ; Cynthia Brandt, MD, MPH ; Arman Cohan, PhD ; and Ron Adelman, MD, MPH, MBA, FACS who all bring expertise in AI and biomedical informatics.

By enhancing the reliability and accuracy of LLMs in health care, this project aims to empower health care professionals with more reliable diagnostic and treatment recommendations, thereby minimizing misinformation risks. Beyond its impact on clinical care, the research will refine the development and evaluation processes of LLMs in biomedicine, providing a roadmap for future AI innovations that prioritize accuracy and trustworthiness.

Sooyoun Tan Web Design and Communications Officer National Institutes of Health (NIH) For media inquiries, please contact us. To learn more, visit the NIH RePORTER page: Qingyu Chen, PhD Assistant Professor of Biomedical Informatics and Data Science Hua Xu, PhD Robert T.

McCluskey Professor of Biomedical Informatics and Data Science Andrew Taylor, MD, MHS Associate Professor Adjunct of Biomedical Informatics and Data Science Cynthia Brandt, MD, MPH Professor of Biomedical Informatics & Data Science Arman Cohan Assistant Professor Ron Adelman, MD, MPH, MBA, FACS Professor Emeritus of Ophthalmology Your browser is antiquated and no longer supported on this website.

Please update your browser or switch to Chrome, Firefox or Safari. You can update your IE here: https://support. microsoft.

com/en-us/help/17621/internet-explorer-downloads