Improving Factual Consistency of Text Summarization by Adversarially Decoupling Comprehension and Embellishment Abilities of LLMs

Despite the recent progress in text summarization made by large language models (LLMs), they often generate summaries that are factually inconsistent with original articles, known as "hallucinations" in text generation. Unlike previous small models (e.g., BART, T5), current LLMs make fewer...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-11
Hauptverfasser:	Feng, Huawen, Fan, Yan, Liu, Xiong, Ting-En Lin, Yao, Zekun, Wu, Yuchuan, Huang, Fei, Li, Yongbin, Ma, Qianli
Format:	Artikel
Sprache:	eng
Schlagworte:	Consistency Decoupling method Hallucinations Large language models Parameter sensitivity
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!