评测中文假信息核查中大模型的能力与局限，发现其易编造事实但可辅助人类工作。
CANDY: Benchmarking LLMs' Limitations and Assistive Potential in Chinese Misinformation Fact-Checking
- 构建2万条中文假信息标注数据集，系统评估大模型表现
- 即使使用思维链和少样本提示，模型准确率仍不高
- 识别出虚构事实是主要错误类型，适合用作人工辅助工具
大语言模型在假信息核查中的有效性仍不明确，尽管其应用日益广泛。为此，我们提出CANDY基准，系统评估大模型在中文假信息核查中的能力与局限。具体而言，我们构建了一个约2万条实例的精心标注数据集。分析表明，即使采用思维链推理和少样本提示，当前大模型在生成准确核查结论方面仍存在明显不足。为理解这些局限，我们建立分类体系，对模型错误解释进行归类，发现事实虚构是最常见的失败模式。虽然大模型单独使用不可靠，但研究结果表明，在实际场景中作为辅助工具，其显著提升人类核查效率的潜力。数据集与代码已开源：https://github.com/SCUNLP/CANDY。
原文摘要 · Abstract (English)
The effectiveness of large language models (LLMs) to fact-check misinformation remains uncertain, despite their growing use. To this end, we present CANDY, a benchmark designed to systematically evaluate the capabilities and limitations of LLMs in fact-checking Chinese misinformation. Specifically, we curate a carefully annotated dataset of ~20k instances. Our analysis shows that current LLMs exhibit limitations in generating accurate fact-checking conclusions, even when enhanced with chain-of-thought reasoning and few-shot prompting. To understand these limitations, we develop a taxonomy to categorize flawed LLM-generated explanations for their conclusions and identify factual fabrication as the most common failure mode. Although LLMs alone are unreliable for fact-checking, our findings indicate their considerable potential to augment human performance when deployed as assistive tools in scenarios. Our dataset and code can be accessed at https://github.com/SCUNLP/CANDY
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。