logo
ResearchBunny Logo
"Why is this misleading?": Detecting News Headline Hallucinations with Explanations

Computer Science

"Why is this misleading?": Detecting News Headline Hallucinations with Explanations

J. Shen, J. Liu, et al.

Discover ExHalder, a groundbreaking framework designed to detect news headline hallucinations. This innovative approach, developed by researchers from Google Research, utilizes insights from public natural language inference datasets to enhance news understanding and generate clear explanations for its findings.

00:00
00:00
Playback language: English
Abstract
This paper introduces ExHalder, a novel framework for detecting news headline hallucinations. ExHalder leverages knowledge from public natural language inference (NLI) datasets, adapting it to the news domain, and generates natural language explanations to justify its predictions. Evaluated on a newly created dataset and six public datasets, ExHalder demonstrates state-of-the-art performance in identifying hallucinated headlines and provides high-quality explanations.
Publisher
Proceedings of the ACM Web Conference 2023 (WWW'23)
Published On
May 01, 2023
Authors
Jiaming Shen, Jialu Liu, Dan Finnie, Negar Rahmati, Michael Bendersky, Marc Najork
Tags
news headline hallucination
natural language inference
framework
ExHalder
explanations
state-of-the-art performance
dataset
Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny