Improving the accuracy of AI language models in healthcare
Official title: Addressing Factual Inaccuracy and Unfaithful Reasoning of Large Language Models in Biomedicine and Healthcare
Funded at Yale University · NIH-10946218 · Data updated 2026-11-12
This study is working to make AI tools used in healthcare more trustworthy, so they give accurate information and help doctors make better decisions, ultimately keeping patients safer and better informed.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Yale University NIH-funded |
| Lab location | 1 site (New Haven, United States) |
| Project start | August 29, 2024 |
| Project end | July 31, 2028 |
| Funding year | 2024 |
| Award (this year) | $375,964 |
| NIH project number | 1R01LM014604-01 |
| Project ID | NIH-10946218 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates for benefiting from this research include patients who rely on AI-assisted tools for medical information and decision-making.
✕Less likely to help
Patients who do not use AI tools or who receive care in settings that do not utilize advanced AI technologies may not benefit from this research.
What this research studies
This research focuses on enhancing the reliability of large language models (LLMs) used in biomedical and healthcare settings. It aims to address issues of factual inaccuracy and unfaithful reasoning in AI-generated responses, which can lead to misinformation and potential misdiagnosis. The project will explore methods for fact-checking and ensuring that AI systems provide evidence-based information, ultimately improving decision-making in healthcare. By refining these AI tools, the research seeks to make them safer and more effective for medical applications.
Why it matters
Potential benefit: If successful, this research could lead to more accurate and trustworthy AI tools that assist healthcare professionals in making better-informed decisions.
How similar studies have gone: Other research has shown promise in improving AI accuracy in various fields, suggesting that similar approaches could be effective in healthcare.
Where this research is happening
-
Yale University
New Haven, United States Active
Researchers
- Principal investigator: Chen, Qingyu — Yale University
- Study coordinator: Chen, Qingyu
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page.