语言模型中的系统性攻击性刻板印象（SOS）偏见
Systematic Offensive Stereotyping (SOS) Bias in Language Models
AI总结：
本文提出衡量语言模型中系统性攻击性刻板印象（SOS）偏见的新指标，发现所有受检模型均存在该偏见，且去偏见方法效果因属性而异，该偏见主要影响仇恨言论检测的公平性而非性能。
摘要：
在本文中，我们提出了一种新指标来衡量语言模型（LMs）中的系统性攻击性刻板印象（SOS）偏见。然后，我们验证了SOS偏见，并调查了消除该偏见的有效性。最后，我们研究了LMs中的SOS偏见对其在仇恨言论检测上的性能和公平性的影响。我们的结果表明，所有受检查的LMs都存在SOS偏见。并且，SOS偏见反映了边缘化群体在网上经历的仇恨。结果表明，使用文献中的去偏见方法会加剧LMs中某些敏感属性的SOS偏见，同时改善其他属性的偏见。最后，我们的结果表明，受检查LMs中的SOS偏见影响了其仇恨言论检测的公平性。然而，没有强有力的证据表明SOS偏见影响仇恨言论检测的性能。
英文摘要：
In this paper, we propose a new metric to measure the SOS bias in language models (LMs). Then, we validate the SOS bias and investigate the effectiveness of removing it. Finally, we investigate the impact of the SOS bias in LMs on their performance and fairness on hate speech detection. Our results suggest that all the inspected LMs are SOS biased. And that the SOS bias is reflective of the online hate experienced by marginalized identities. The results indicate that using debias methods from the literature worsens the SOS bias in LMs for some sensitive attributes and improves it for others. Finally, Our results suggest that the SOS bias in the inspected LMs has an impact on their fairness of hate speech detection. However, there is no strong evidence that the SOS bias has an impact on the performance of hate speech detection.
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。
