Machine-generated text is increasingly difficult to distinguish from text authored by humans.
Powerful open-source models are freely available, and user-friendly tools that democratize …

Text Generation aims to produce plausible and readable text in human language from input
data. The resurgence of deep learning has greatly advanced this field, in particular, with the …

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 …

Pretrained language models (PLM) have recently advanced graph-to-text generation, where
the input graph is linearized into a sequence and fed into the PLM to obtain its …

A major challenge in evaluating data-to-text (D2T) generation is measuring the semantic
accuracy of the generated text, ie checking if the output text contains all and only facts …

We address the issue of hallucination in data-to-text generation, ie, reducing the generation
of text that is unsupported by the source. We conjecture that hallucination can be caused by …

In data-to-text (D2T) generation, training on in-domain data leads to overfitting to the data
representation and repeating training data noise. We examine how to avoid finetuning …

Large language models (LLMs) have been widely employed for graph-to-text generation
tasks. However, the process of finetuning LLMs requires significant training resources and …

Prefix-tuning is a powerful lightweight technique for adapting a large pre-trained language
model to a downstream application. However, it uses the same dataset-level tuned prompt …

Text generation from semantic parses is to generate textual descriptions for formal
representation inputs such as logic forms and SQL queries. This is challenging due to two …