arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.10281cs.CLcs.AIcs.LG
收藏

Trifecta团队在Factify5WQA中:以微调树立事实核查标准

Team Trifecta at Factify5WQA: Setting the Standard in Fact Verification with Fine-Tuning

National Yang Ming Chiao Tung University(阳明交通大学)

Shang-Hsuan Chiang, Ming-Chih Lo, Lin-Wei Chao, Wen-Chih Peng

AI总结:

我们提出Pre-CoFactv3框架,结合问答、文本分类、上下文学习、微调LLM及FakeNet模型,在AAAI-24 Factify 3.0中获第一,准确率超基线103%,领先第二名70%。

摘要:

在本文中,我们提出了Pre-CoFactv3,一个由问答和文本分类组件组成的综合框架,用于事实核查。利用上下文学习、微调大型语言模型(LLMs)以及FakeNet模型,我们解决了事实核查中的挑战。我们的实验探索了多种方法,比较了不同的预训练LLMs,引入了FakeNet,并实施了多种集成方法。值得注意的是,我们的团队Trifecta在AAAI-24 Factify 3.0研讨会中荣获第一名,将基线准确率提升了103%,并领先第二名70%。这一成功凸显了我们方法的有效性及其对推进事实核查研究的潜在贡献。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑