AI能准确判断假信息，但理由靠语言特征而非真实可信度。
GenAI vs. Human Fact-Checkers: Accurate Ratings, Flawed Rationales
- 用语言特征和形式化标准判断内容可信度，而非真正理解真假。
- GPT-4o表现最好，但与人工标注者一致性仅中等。
- 摘要输入可提升效率且不牺牲准确率，适合辅助人工核查。
尽管生成式人工智能（GenAI）能力不断进步，我们对其评估和推理信息真伪的能力仍了解有限。本文在涉及内容可信度评分及推理判断的任务上，评估了多个GenAI模型的表现，数据来自美国次国家级政客在Facebook发布的帖子。结果发现，目前最常用的消费者级模型GPT-4o表现最佳，但所有模型与人类标注者的一致性仅为中等水平。值得注意的是，即使模型能正确识别低可信度内容，其推理依据主要依赖于语言特征和‘硬性’标准，如细节程度、来源可靠性及语言正式性，而非对真实性的真实理解。我们还对比了摘要与完整内容输入的效果，发现摘要输入在保持准确率的同时显著提升处理效率，具有应用潜力。尽管GenAI有辅助人工事实核查以应对虚假信息规模化的前景，但结果警示：不可完全依赖这些模型。
原文摘要 · Abstract (English)
Despite recent advances in understanding the capabilities and limits of generative artificial intelligence (GenAI) models, we are just beginning to understand their capacity to assess and reason about the veracity of content. We evaluate multiple GenAI models across tasks that involve the rating of, and perceived reasoning about, the credibility of information. The information in our experiments comes from content that subnational U.S. politicians post to Facebook. We find that GPT-4o, one of the most used AI models in consumer applications, outperforms other models, but all models exhibit only moderate agreement with human coders. Importantly, even when GenAI models accurately identify low-credibility content, their reasoning relies heavily on linguistic features and ``hard'' criteria, such as the level of detail, source reliability, and language formality, rather than an understanding of veracity. We also assess the effectiveness of summarized versus full content inputs, finding that summarized content holds promise for improving efficiency without sacrificing accuracy. While GenAI has the potential to support human fact-checkers in scaling misinformation detection, our results caution against relying solely on these models.
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。