4 papers
Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines
Yuchen Li, Alexandre Kirchmeyer, Aashay Mehta +5
Autoregressive language models are the currently dominant paradigm for text generation, but they have some fundamental limitations that cannot be remedied by scale-for example inhe…
Fit Like You Sample: Sample-Efficient Generalized Score Matching from Fast Mixing Diffusions
Yilong Qin, Andrej Risteski
Score matching is an approach to learning probability distributions parametrized up to a constant of proportionality (e.g. Energy-Based Models). The idea is to fit the score of the…
Characterizing Out-of-Distribution Error via Optimal Transport
Yuzhe Lu, Yilong Qin, Runtian Zhai +7
Out-of-distribution (OOD) data poses serious challenges in deployed machine learning models, so methods of predicting a model's performance on OOD data without labels are important…
Powering Comparative Classification with Sentiment Analysis via Domain Adaptive Knowledge Transfer
Zeyu Li, Yilong Qin, Zihan Liu +1
We study Comparative Preference Classification (CPC) which aims at predicting whether a preference comparison exists between two entities in a given sentence and, if so, which enti…