Skip to main content
ASP2024: A Virtual Conference Main banner
Final Program


Schedule-at-a-Glance
Icon Legend
This session is not in your schedule.
This session is in your schedule. Click again to remove it.
Back
Session VIDEO link

Teaching Astronomy – New Opportunities, Challenges, Tools, and Innovations

Session: 12C: 10-Minute Orals (4)

12C-2 - Fine Tuning Large Language Models to Identify Science Misinformation

Saturday, August 24, 2024
10:50 AM – 11:40 AM US PDT
Abstract: In the last year, tremendous advances have been made in Artificial Intelligence and Machine Learning. For this project we created a unique data set of curated and tagged articles about ten science topics where misinformation is abundant. This initial data set was used to generate an even larger corpus of data that was used to train a machine learning algorithm to detect science misinformation. This algorithm was successfully deployed but is limited to reporting a probability that the information is real or fake. After this successful proof-of-concept, the data was used to fine-tune several state-of-the art Large Language Models (LLMs). These LLMs have the ability not only to assess articles for misinformation, but also to interact with users and provide meaningful feedback that explains which information is incorrect, and why. Instructors and students will be able to use these trained LLMs to help check sources and identify misinformation for projects and papers.