Search papers, labs, and topics across Lattice.
University of Notre Dame
3
0
6
RL fine-tuning can *hurt* reasoning performance when your base LLM is already too good, unless you force it to explore more diverse solutions.
LLMs still struggle to apply public policy knowledge in real-world scenarios, even when they can memorize facts and understand concepts.
Soft-gating with an "advisor" model can steer LLMs to be safer and more useful, reducing over-refusal without sacrificing detection accuracy.
