Human variation in labeling is often considered noise. Annotation projects for machine
learning (ML) aim at minimizing human label variation, with the assumption to maximize …

Large-scale language models often learn behaviors that are misaligned with user
expectations. Generated text may contain offensive or toxic language, contain significant …

Capturing accurate uncertainty quantification of the prediction from deep neural networks is
important in many real-world decision-making applications. A reliable predictor is expected …

Today's probabilistic language generators fall short when it comes to producing coherent
and fluent text despite the fact that the underlying models perform well under standard …

Previous work has proposed many new loss functions and regularizers that improve test
accuracy on image classification tasks. However, it is not clear whether these loss functions …

Deep learning models often raise privacy concerns as they leak information about their
training data. This leakage enables membership inference attacks (MIA) that can identify …

Abstract Language models (LMs) compute the probability of a text by sequentially computing
a representation of an already-seen context and using this representation to predict the next …

As machine learning models in critical fields increasingly grapple with multimodal data, they
face the dual challenges of handling a wide array of modalities, often incomplete due to …

Large language models (LMs) are capable of generating free-text rationales to aid question
answering. However, prior work 1) suggests that useful self-rationalization is emergent only …

Current neural language models are trained to minimize cross-entropy and use softmax to
compute the locally normalized probabilities over the target. While this setup provides solid …