As language models become more powerful, training and evaluation are increasingly
bottlenecked by the data and metrics used for a particular task. For example, summarization …

Chain-of-thought prompting (eg," Let's think step-by-step") primes large language models to
verbalize rationalization for their predictions. While chain-of-thought can lead to dramatic …

The potential for pre-trained large language models (LLMs) to use natural language
feedback at inference time has been an exciting recent development. We build upon this …

Natural language explanations (NLEs) are a special form of data annotation in which
annotators identify rationales (most significant text tokens) when assigning labels to data …

Recently generating natural language explanations has shown very promising results in not
only offering interpretable explanations but also providing additional information and …

Grounding referring expressions in images aims to locate the object instance in an image
described by a referring expression. It involves a joint understanding of natural language …

Pretrained language models often do not perform tasks in ways that are in line with our
preferences, eg, generating offensive text or factually incorrect summaries. Recent work …

Pretrained language models often do not perform tasks in ways that are in line with our
preferences, eg, generating offensive text or factually incorrect summaries. Recent work …

Eliciting feedback from end users of NLP models can be beneficial for improving models.
However, how should we present model responses to users so they are most amenable to …

The goal of unpaired image captioning (UIC) is to describe images without using image-
caption pairs in the training phase. Although challenging, we expect the task can be …