arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.13865cs.CL
收藏

缺少反证据致使NLP事实核查因错误信息而不切实际

Missing Counter-Evidence Renders NLP Fact-Checking Unrealistic for Misinformation

Technical University of Darmstadt(达姆施塔特工业大学);Hessian Center for AI (hessian.AI)(黑森人工智能中心(hessian.AI));IBM Research Europe(IBM欧洲研究院)

Max Glockner, Yufang Hou, Iryna Gurevych

摘要:

错误信息出现在不确定的时候,当可信的信息是有限的。这对于基于NLP的事实核查来说是一个挑战,因为它依赖于可能尚未获得的反证。尽管人们对自动事实核查的兴趣越来越大,但目前仍不清楚自动化方法是否能够切实地驳斥有害的现实世界错误信息。在这里,我们将NLP事实核查与专业事实核查人员如何在没有反证的情况下打击错误信息进行对比和比较。在我们的分析中,我们表明,通过设计,现有的事实核查NLP任务定义不能像专业事实核查人员对大多数索赔那样反驳错误信息。然后,我们定义了数据集中的证据必须满足现实事实核查的两个要求:它必须(1)足以反驳索赔,(2)不从现有的事实核查文章中泄露。我们调查了现有的事实核查数据集,发现它们都未能满足这两个标准。最后,我们进行了实验,以证明在大规模事实检查数据集上训练的模型依赖于泄露的证据,这使得它们不适合现实世界的场景。综上所述,我们表明,目前的NLP事实检查无法切实打击现实世界的错误信息,因为它依赖于对数据中反证的不切实际的假设。

英文摘要:

Misinformation emerges in times of uncertainty when credible information is limited. This is challenging for NLP-based fact-checking as it relies on counter-evidence, which may not yet be available. Despite increasing interest in automatic fact-checking, it is still unclear if automated approaches can realistically refute harmful real-world misinformation. Here, we contrast and compare NLP fact-checking with how professional fact-checkers combat misinformation in the absence of counter-evidence. In our analysis, we show that, by design, existing NLP task definitions for fact-checking cannot refute misinformation as professional fact-checkers do for the majority of claims. We then define two requirements that the evidence in datasets must fulfill for realistic fact-checking: It must be (1) sufficient to refute the claim and (2) not leaked from existing fact-checking articles. We survey existing fact-checking datasets and find that all of them fail to satisfy both criteria. Finally, we perform experiments to demonstrate that models trained on a large-scale fact-checking dataset rely on leaked evidence, which makes them unsuitable in real-world scenarios. Taken together, we show that current NLP fact-checking cannot realistically combat real-world misinformation because it depends on unrealistic assumptions about counter-evidence in the data.

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。

↑