Improving the reliability of simplified medical information using AI language models
Building Safety Guards into LLMs for Trustworthy Automatic Simplification of Medical Documents
['FUNDING_R01'] · UNIVERSITY OF TEXAS AT AUSTIN · NIH-10944659
This study is working on making medical information easier to understand and more reliable by using advanced technology to spot mistakes in simplified texts, so everyone can access trustworthy health knowledge and feel more confident about their health decisions.
Quick facts
| Phase | ['FUNDING_R01'] |
|---|---|
| Study type | Nih_funding |
| Sex | All |
| Sponsor | UNIVERSITY OF TEXAS AT AUSTIN (nih funded) |
| Locations | 1 site (AUSTIN, UNITED STATES) |
| Trial ID | NIH-10944659 on ClinicalTrials.gov |
What this research studies
This research aims to enhance the accuracy and reliability of simplified medical documents generated by large language models (LLMs) like ChatGPT. It focuses on developing new natural language processing technologies that can detect errors in the simplified texts, ensuring that the information provided to the public is both accessible and trustworthy. By creating tools that help communities critically evaluate LLM outputs, the project seeks to improve health literacy and empower individuals with better access to medical knowledge. The approach includes building controllable and transparent LLMs that can safely simplify complex medical literature.
Who could benefit from this research
Good fit: Ideal candidates for benefiting from this research include individuals seeking reliable medical information in simpler language, particularly those with limited health literacy.
Not a fit: Patients who are already well-versed in medical terminology and have access to peer-reviewed literature may not find this research beneficial.
Why it matters
Potential benefit: If successful, this research could provide patients and the general public with more accurate and understandable medical information, enhancing their ability to make informed health decisions.
How similar studies have performed: While the use of LLMs for simplifying medical texts is a novel approach, there have been successful applications of AI in other areas of healthcare communication.
Where this research is happening
AUSTIN, UNITED STATES
- UNIVERSITY OF TEXAS AT AUSTIN — AUSTIN, UNITED STATES (ACTIVE)
Researchers
- Principal investigator: LI, JUNYI JESSY — UNIVERSITY OF TEXAS AT AUSTIN
- Study coordinator: LI, JUNYI JESSY
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 below.