Long documents such as academic articles and business reports have been the standard
format to detail out important issues and complicated subjects that require extra attention. An …

Multi-document summarization is a challenging task for which there exists little large-scale
datasets. We propose Multi-XScience, a large-scale multi-document summarization dataset …

Pretraining techniques leveraging enormous datasets have driven recent advances in text
summarization. While folk explanations suggest that knowledge transfer accounts for …

We propose an unsupervised graph-based ranking model for extractive summarization of
long scientific documents. Our method assumes a two-level hierarchical graph …

With the explosive growth of livestream broadcasting, there is an urgent need for new
summarization technology that enables us to create a preview of streamed content and tap …

We characterize and study zero-shot abstractive summarization in Large Language Models
(LLMs) by measuring position bias, which we propose as a general formulation of the more …

In this paper, we propose FFCI, a framework for fine-grained summarization evaluation that
comprises four elements: faithfulness (degree of factual consistency with the source), focus …

A typical journalistic convention in news articles is to deliver the most salient information in
the beginning, also known as the lead bias. While this phenomenon can be exploited in …

Meeting minutes record any subject matters discussed, decisions reached and actions taken
at meetings. The importance of minuting cannot be overemphasized in a time when a …

In news articles the lead bias is a common phenomenon that usually dominates the learning
signals for neural extractive summarizers, severely limiting their performance on data with …