Towards LLM-based fact verification on news claims with a hierarchical step-by-step prompting method
Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
11-2023
Abstract
While large pre-trained language models (LLMs) have shown their impressive capabilities in various NLP tasks, they are still underexplored in the misinformation domain. In this paper, we examine LLMs with in-context learning (ICL) for news claim verification, and find that only with 4-shot demonstration examples, the performance of several prompting methods can be comparable with previous supervised models. To further boost performance, we introduce a Hierarchical Step-by-Step (HiSS) prompting method which directs LLMs to separate a claim into several subclaims and then verify each of them via multiple questionsanswering steps progressively. Experiment results on two public misinformation datasets show that HiSS prompting outperforms stateof-the-art fully-supervised approach and strong few-shot ICL-enabled baselines.
Discipline
Programming Languages and Compilers | Software Engineering
Research Areas
Data Science and Engineering
Publication
Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, Bali, Indonesia, November 1-4
First Page
996
Last Page
1011
Publisher
Association for Computational Linguistics
City or Country
New York, USA
Citation
ZHANG, Xuan and GAO, Wei.
Towards LLM-based fact verification on news claims with a hierarchical step-by-step prompting method. (2023). Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, Bali, Indonesia, November 1-4. 996-1011.
Available at: https://ink.library.smu.edu.sg/sis_research/8453
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.