4 papers · 1 filter
Scaling Test-Time Compute Without Verification or RL is Suboptimal
Amrith Setlur, Nived Rajaraman, Sergey Levine +1
Despite substantial advances in scaling test-time compute, an ongoing debate in the community is how it should be scaled up to enable continued and efficient improvements with scal…
What Do Learning Dynamics Reveal About Generalization in LLM Reasoning?
Katie Kang, Amrith Setlur, Dibya Ghosh +4
Despite the remarkable capabilities of modern large language models (LLMs), the mechanisms behind their problem-solving abilities remain elusive. In this work, we aim to better und…
Unfamiliar Finetuning Examples Control How Language Models Hallucinate
Katie Kang, Eric Wallace, Claire Tomlin +2
Large language models are known to hallucinate when faced with unfamiliar queries, but the underlying mechanism that govern how models hallucinate are not yet fully understood. In…
Deep Neural Networks Tend To Extrapolate Predictably
Katie Kang, Amrith Setlur, Claire Tomlin +1
Conventional wisdom suggests that neural network predictions tend to be unpredictable and overconfident when faced with out-of-distribution (OOD) inputs. Our work reassesses this a…