Do LLMs Know When They Are Wrong About Molecules? In-Context Property Prediction with Self-Reported Uncertainty
This work evaluates the capability of 7 frontier LLMs to predict molecular properties together with a self-reported uncertainty from in-context examples, and compares them with classical baselines trained on the same molecules.
Matthias Busch, M. Tacke, Tamadur Albaraghtheh et al.
· 0 citations