A hallucination detection and mitigation framework for faithful text summarization using LLMs

Abstract Recent advancements in large language models (LLMs) have significantly propelled the field of automatic text summarization. Nevertheless, the domain continues to face substantial challenges, particularly the issue of hallucination where summaries contain information not present in the sourc...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Shenling Liu, Yang Gao, ShaSha Li, PanCheng Wang, Ting Wang
Format:	Artigo
Sprog:	Inglês
Udgivet:	Nature Portfolio 2025-12-01
Serier:	Scientific Reports
Fag:	Text summarization Hallucination detection Q-S-E methodology Factual accuracy
Online adgang:	https://doi.org/10.1038/s41598-025-31075-1
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!