2 papers
cs.LG2024
Improving Black-box Robustness with In-Context Rewriting
Kyle O'Brien, Nathan Ng, Isha Puri +5
Machine learning models for text classification often excel on in-distribution (ID) data but struggle with unseen out-of-distribution (OOD) inputs. Most techniques for improving OO…
cs.LG2024
Measuring Stochastic Data Complexity with Boltzmann Influence Functions
Nathan Ng, Roger Grosse, Marzyeh Ghassemi
Estimating the uncertainty of a model's prediction on a test point is a crucial part of ensuring reliability and calibration under distribution shifts. A minimum description length…