微调 Transformer 在事实核查上相较于更大语言模型的惊人效能
Surprising Efficacy of Fine-Tuned Transformers for Fact-Checking over Larger Language Models
AI总结：
本文通过覆盖 90 多种语言的现实世界基准，证明微调 Transformer 在声明检测和真实性预测上优于 GPT-4 等大语言模型，而 LLMs 在问题分解等生成式任务中更具优势。
摘要：
在本文中，我们探讨了在覆盖 90 多种语言的现实世界环境中建立端到端事实核查流水线所面临的挑战。我们的现实世界实验基准表明，专门针对事实核查任务（如声明检测和真实性预测）微调 Transformer 模型，能够提供优于 GPT-4、GPT-3.5-Turbo 和 Mistral-7b 等大语言模型（LLMs）的性能。然而，我们说明 LLMs 在生成式任务（如用于证据检索的问题分解）中表现出色。通过广泛评估，我们展示了微调模型在多语言环境以及包含数值量的复杂声明中进行事实核查的效能。
英文摘要：
In this paper, we explore the challenges associated with establishing an end-to-end fact-checking pipeline in a real-world context, covering over 90 languages. Our real-world experimental benchmarks demonstrate that fine-tuning Transformer models specifically for fact-checking tasks, such as claim detection and veracity prediction, provide superior performance over large language models (LLMs) like GPT-4, GPT-3.5-Turbo, and Mistral-7b. However, we illustrate that LLMs excel in generative tasks such as question decomposition for evidence retrieval. Through extensive evaluation, we show the efficacy of fine-tuned models for fact-checking in a multilingual setting and complex claims that include numerical quantities.
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。
