2 papers
cs.LG2026
Sparse probes and murky physics: a case study of interpretability challenges in a foundation model for continuum dynamics
Katherine Rosenfeld, Maike Sonnewald
Generative AI emulators are increasingly used in scientific domains where we already have strong theory, benchmarks, and physical intuition. This raises a central evaluation and in…
cs.CL2024
Building Understandable Messaging for Policy and Evidence Review (BUMPER) with AI
Katherine A. Rosenfeld, Maike Sonnewald, Sonia J. Jindal +2
We introduce a framework for the use of large language models (LLMs) in Building Understandable Messaging for Policy and Evidence Review (BUMPER). LLMs are proving capable of provi…