Natural Language Generation (NLG) has improved exponentially in recent years thanks to
the development of sequence-to-sequence deep learning technologies such as Transformer …

Large pre-trained models, also known as foundation models (FMs), are trained in a task-
agnostic manner on large-scale data and can be adapted to a wide range of downstream …

Ensuring alignment, which refers to making models behave in accordance with human
intentions [1, 2], has become a critical task before deploying large language models (LLMs) …

Challenging problems such as open-domain question answering, fact checking, slot filling
and entity linking require access to large, external knowledge sources. While some models …

The goal of text-to-text generation is to make machines express like a human in many
applications such as conversation, summarization, and translation. It is one of the most …

We present DART, an open domain structured DAta Record to Text generation dataset with
over 82k instances (DARTs). Data-to-Text annotations can be a costly process, especially …

Understanding narratives requires reasoning about implicit world knowledge related to the
causes, effects, and states of situations described in text. At the core of this challenge is how …

Graphs that capture relations between textual units have great benefits for detecting salient
information from multiple documents and generating overall coherent summaries. In this …

Sequence-to-sequence models for abstractive summarization have been studied
extensively, yet the generated summaries commonly suffer from fabricated content, and are …

Abstractive conversation summarization has received much attention recently. However,
these generated summaries often suffer from insufficient, redundant, or incorrect content …