Loading...

Zero-Shot Learning and Key Points Are All You Need for Automated Fact-Checking

Mohammadkhani, M. G ; Sharif University of Technology | 2024

158 Viewed
  1. Type of Document: Article
  2. Publisher: 2024
  3. Abstract:
  4. Automated fact-checking is an important task because determining the accurate status of a proposed claim within the vast amount of information available online is a critical challenge. This challenge requires robust evaluation to prevent the spread of false information. Modern large language models (LLMs) have demonstrated high capability in performing a diverse range of Natural Language Processing (NLP) tasks. By utilizing proper prompting strategies, their versatility—due to their understanding of large context sizes and zero-shot learning ability—enables them to simulate human problem-solving intuition and move towards being an alternative to humans for solving problems. In this work, we introduce a straightforward framework based on Zero-Shot Learning and Key Points (ZSL-KeP) for automated fact-checking, which despite its simplicity, performed well on the AVeriTeC shared task dataset by robustly improving the baseline and achieving 10th place. © 2024 Association for Computational Linguistics
  5. Keywords:
  6. Adversarial machine learning ; Computational linguistics ; Contrastive Learning ; Natural language processing systems ; Amount of information ; Critical challenges ; Diverse range ; High capabilities ; Human problem solving ; Keypoints ; Language model ; Language processing ; Learning abilities ; Natural languages ; Zero-shot learning
  7. Source: FEVER 2024 - 7th Fact Extraction and VERification Workshop, Proceedings of the Workshop ; 2024 , Pages 86-90 ; 979-889176172-8 (ISBN)
  8. URL: https://aclanthology.org/2024.fever-1.9