Official websites use .gov

A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS

A lock ( 🔒 ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Need Help

Living, Iterative Validation and Evaluation of AI in Medicine

Award Number: R01LM014795
ORGANIZATION: NATIONAL LIBRARY OF MEDICINE
OPDIV: NIH
AWARD CLASS: DISCRETIONARY
AWARD ACTIVITY TYPE: SCIENTIFIC/HEALTH RESEARCH (INCLUDES SURVEYS)
PERIOD OF PERFORMANCE START DATE: 06/15/2026
PERIOD OF PERFORMANCE END DATE: 04/30/2031

Group Awards By:

View Award Description

Living, Iterative Validation and Evaluation of AI in Medicine - Project Summary Foundation models (FMs), including large language models (LLMs), have created immense promise and excitement with their potential to change multiple aspects of how we pursue the science, practice and delivery of medicine. Given the potential, there is a need to create systematic ways to verify presumed benefits of using LLMs for medical tasks. The challenges in discerning hype from benefit are largely due to the absence of shared benchmarks that enable consistent evaluation (benchmarking), little guidance on trade-offs in performance for different post-training strategies (adaptation recipes), and a dearth of studies on the optimal mode of combining human expertise with models (human-AI teaming). We investigate methods to systematically evaluate LLMs in a setting where there is interaction between human experts to generate reusable guidance for performance benchmarking, adaptation recipes using human preferences, and implementing human-ai teaming in clinical settings. If successful, we will develop and implement concrete procedures to verify benefits of using LLMs in the context of the clinical tasks for which they are used. Overall, we seek to improve the creation and evaluation of foundation models in healthcare by rigorous benchmarking, developing systematic adaptation recipes, and guidance for optimal human-AI teaming setups.


Issue Date FY	Funding FY	Legal Entity Name	Legal Entity Address	Legal Entity City	Legal Entity State	Legal Entity Zip Code	Legal Entity COUNTY	Legal Entity COUNTRY	Assistance Listing	Award Code	Budget Year	Action Date	Action Type	Action Amount

Issue Date FY: 2026 ( Subtotal = $652,850 )
2026	2026	THE LELAND STANFORD JUNIOR UNIVERSITY	450 JANE STANFORD WAY	STANFORD	CA	94305	SANTA CLARA	USA	Medical Library Assistance	000	1	6/16/2026	NEW	$652,850
														Subtotal = $652,850

Grand Total All Awards = $652,850

Top

All Categories

About

Search

Reports

Data Submission

Award Information

Living, Iterative Validation and Evaluation of AI in Medicine

Award Number: R01LM014795

ORGANIZATION: NATIONAL LIBRARY OF MEDICINE

OPDIV: NIH

AWARD CLASS: DISCRETIONARY

AWARD ACTIVITY TYPE: SCIENTIFIC/HEALTH RESEARCH (INCLUDES SURVEYS)

PERIOD OF PERFORMANCE START DATE: 06/15/2026

PERIOD OF PERFORMANCE END DATE: 04/30/2031

Federal Websites

Department of Health & Human Services

HHS Operating Divisions

HHS Staff Divisions

Download A Document Viewer