Explainable NLP (ExNLP) has increasingly focused on collecting human-annotated textual
explanations. These explanations are used downstream in three ways: as data …

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 …

Abstract Large Language Models (LLMs) can achieve strong performance on many tasks by
producing step-by-step reasoning before giving a final output, often referred to as chain-of …

Deploying large language models (LLMs) is challenging because they are memory
inefficient and compute-intensive for practical applications. In reaction, researchers train …

We explore how generating a chain of thought---a series of intermediate reasoning steps---
significantly improves the ability of large language models to perform complex reasoning. In …

Does prompting a large language model (LLM) like GPT-3 with explanations improve in-
context learning? We study this question on two NLP tasks that involve reasoning over text …

Breaking down a problem into intermediate steps has demonstrated impressive
performance in Large Language Model (LLM) reasoning. However, the growth of the …

Pretrained language models often generate outputs that are not in line with human
preferences, such as harmful text or factually incorrect summaries. Recent work approaches …

Large language models are increasingly capable of generating fluent-appearing text with
relatively little task-specific supervision. But can these models accurately explain …

Integrating free-text explanations to in-context learning of large language models (LLM) is
shown to elicit strong reasoning capabilities along with reasonable explanations. In this …