As the societal impact of Deep Neural Networks (DNNs) grows, the goals for advancing
DNNs become more complex and diverse, ranging from improving a conventional model …

Recent work has shown that incorporating explanations into the output generated by large
language models (LLMs) can significantly enhance performance on a broad spectrum of …

Rationalization aims to strengthen the interpretability of NLP models by extracting a subset
of human-intelligible pieces of their inputting texts. Conventional works generally employ the …

Despite being highly performant, deep neural networks might base their decisions on
features that spuriously correlate with the provided labels, thus hurting generalization. To …

Neural metrics for machine translation evaluation, such as COMET, exhibit significant
improvements in their correlation with human judgments, as compared to traditional metrics …

Deep neural networks have emerged as highly effective tools for computer vision systems,
showcasing remarkable performance. However, the intrinsic opacity, potential biases, and …

Recent work has shown that inducing a large language model (LLM) to generate
explanations prior to outputting an answer is an effective strategy to improve performance on …

Rationalization empowers deep learning models with self-explaining capabilities through a
cooperative game, where a generator selects a semantically consistent subset of the input …

The ability to extrapolate, ie, to make predictions on sequences that are longer than those
presented as training examples, is a challenging problem for current deep learning models …

Large Language Models (LLMs) have significantly advanced the field of Natural Language
Processing (NLP), but their lack of interpretability has been a major concern. Current …