解构针对不同目标身份的仇恨言论
Disentangling Hate Across Target Identities
AI总结：
研究分析仇恨言论分类器在针对不同目标身份时的表现差异与系统性偏差，发现模型仅因提及特定身份就提高仇恨得分且混淆仇恨性与情感极性，可能误伤弱势群体，并揭示预测准确性与刻板印象强度强相关。
摘要：
仇恨言论（HS）分类器在检测针对不同目标身份的仇恨表达时表现并不一致。它们在预测仇恨得分时也表现出系统性偏差。利用最近提出的两个用于HS检测的功能性测试数据集，我们定量分析了不同因素对HS预测的影响。在流行的工业界和学术界模型上的实验表明，HS检测器仅基于特定目标身份的提及就会赋予更高的仇恨得分。此外，模型常将仇恨性与情感极性混淆。这一结果令人担忧，因为构建HS检测器的努力可能会损害我们希望保护的弱势身份群体：表达对仇恨言论愤怒或反对的帖子可能被标记为仇恨言论。我们还开展了一项受社会心理学理论启发的研究，揭示仇恨性预测的准确性与刻板印象强度强相关。
英文摘要：
Hate speech (HS) classifiers do not perform equally well in detecting hateful expressions towards different target identities. They also demonstrate systematic biases in predicted hatefulness scores. Tapping on two recently proposed functionality test datasets for HS detection, we quantitatively analyze the impact of different factors on HS prediction. Experiments on popular industrial and academic models demonstrate that HS detectors assign a higher hatefulness score merely based on the mention of specific target identities. Besides, models often confuse hatefulness and the polarity of emotions. This result is worrisome as the effort to build HS detectors might harm the vulnerable identity groups we wish to protect: posts expressing anger or disapproval of hate expressions might be flagged as hateful themselves. We also carry out a study inspired by social psychology theory, which reveals that the accuracy of hatefulness prediction correlates strongly with the intensity of the stereotype.
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。
