TELLER : A Trustworthy Framework for Explainable, Generalizable and Controllable Fake News Detection

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationFindings of the Association for Computational Linguistics ACL 2024
EditorsLun-Wei Ku, Andre Martins, Vivek Srikumar
PublisherAssociation for Computational Linguistics
Pages15556-15583
ISBN (print)979-8-89176-099-8
Publication statusPublished - Aug 2024

Conference

Title62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024)
LocationCentara Grand and Bangkok Convention Centre
PlaceThailand
CityBangkok
Period11 - 16 August 2024

Link(s)

Abstract

The proliferation of fake news has emerged as a severe societal problem, raising significant interest from industry and academia. While existing deep-learning based methods have made progress in detecting fake news accurately, their reliability may be compromised caused by the non-transparent reasoning processes, poor generalization abilities and inherent risks of integration with large language models (LLMs). To address this challenge, we propose TELLER, a novel framework for trustworthy fake news detection that prioritizes explainability, generalizability and controllability of models. This is achieved via a dual-system framework that integrates cognition and decision systems, adhering to the principles above. The cognition system harnesses human expertise to generate logical predicates, which guide LLMs in generating human-readable logic atoms. Meanwhile, the decision system deduces generalizable logic rules to aggregate these atoms, enabling the identification of the truthfulness of the input news across diverse domains and enhancing transparency in the decision-making process. Finally, we present comprehensive evaluation results on four datasets, demonstrating the feasibility and trustworthiness of our proposed framework. Our implementation is available at this link1. ©2024 Association for Computational Linguistics.

Research Area(s)

Bibliographic Note

Research Unit(s) information for this publication is provided by the author(s) concerned.

Citation Format(s)

TELLER: A Trustworthy Framework for Explainable, Generalizable and Controllable Fake News Detection. / Liu, Hui; Wang, Wenya; Li, Haoru et al.
Findings of the Association for Computational Linguistics ACL 2024. ed. / Lun-Wei Ku; Andre Martins; Vivek Srikumar. Association for Computational Linguistics, 2024. p. 15556-15583.

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

Download Statistics

No data available