AI RESEARCH
In-Context Molecular Property Prediction with LLMs: A Blinding Study on Memorization and Knowledge Conflicts
arXiv CS.LG
•
ArXi:2603.25857v1 Announce Type: new The capabilities of large language models (LLMs) have expanded beyond natural language processing to scientific prediction tasks, including molecular property prediction. However, their effectiveness in in-context learning remains ambiguous, particularly given the potential for