In this paper, we present Pre-CoFactv3, a comprehensive framework comprised of Question Answering and Text Classification components for fact verification. Leveraging In-Context Learning, Fine-tuned Large Language Models (LLMs), and the FakeNet model, we address the challenges of fact verification. Our experiments explore diverse approaches, comparing different Pre-trained LLMs, introducing FakeNet, and implementing various ensemble methods. Notably, our team, Trifecta, secured first place in the AAAI-24 Factify 3.0 Workshop, surpassing the baseline accuracy by 103% and maintaining a 70% lead over the second competitor. This success underscores the efficacy of our approach and its potential contributions to advancing fact verification research.
@article{arxiv.2403.10281,
title = {Team Trifecta at Factify5WQA: Setting the Standard in Fact Verification with Fine-Tuning},
author = {Shang-Hsuan Chiang and Ming-Chih Lo and Lin-Wei Chao and Wen-Chih Peng},
journal= {arXiv preprint arXiv:2403.10281},
year = {2024}
}
Comments
Accepted by AAAI 2024 Workshop: FACTIFY 3.0 - Workshop Series on Multimodal Fact-Checking and Hate Speech Detection