TELLER: A Trustworthy Framework for Explainable, Generalizable and Controllable Fake News Detection
This addresses the societal issue of fake news by enhancing trustworthiness in detection systems, though it is incremental in combining existing elements like human expertise and logic rules.
The authors tackled the problem of unreliable fake news detection by proposing TELLER, a framework that integrates human expertise and logical reasoning to improve explainability, generalizability, and controllability, achieving competitive performance across four datasets.
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 {\methodname}, 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 \url{https://github.com/less-and-less-bugs/Trust_TELLER}.