Counteracts：测试预训练语言模型中的刻板印象表征
Counteracts: Testing Stereotypical Representation in Pre-trained Language Models
AI总结：
本文提出使用反例检验预训练语言模型中的内部刻板印象知识，在9种完形填空式提示上评估7个模型，发现其对无关信息和浅层语言线索具鲁棒性但缺乏按意义解释信息的能力，为中立微调与评估提供启示。
摘要：
近期，语言模型在各种自然语言理解任务上展现出强大性能。基于大型人类生成语料库训练的语言模型不仅编码了大量人类知识，也编码了人类的刻板印象。随着越来越多的下游任务将语言模型作为流程的一部分，有必要理解内部的刻板印象表征，从而设计方法以减轻其负面影响。本文使用反例来检验预训练语言模型（PLMs）中可能导致刻板印象偏好的内部刻板印象知识。我们主要关注性别刻板印象，但该方法可扩展至其他类型的刻板印象。我们在9种具有不同信息和基础知识的完形填空式提示上评估了7个PLMs。结果表明，PLMs对无关信息及对词位置和句法结构等浅层语言线索的偏好表现出一定鲁棒性，但缺乏按意义解释信息的能力。这些发现为如何在微调和评估中以中立方式与PLMs交互提供了启示。
英文摘要：
Recently, language models have demonstrated strong performance on various natural language understanding tasks. Language models trained on large human-generated corpus encode not only a significant amount of human knowledge, but also the human stereotype. As more and more downstream tasks have integrated language models as part of the pipeline, it is necessary to understand the internal stereotypical representation in order to design the methods for mitigating the negative effects. In this paper, we use counterexamples to examine the internal stereotypical knowledge in pre-trained language models (PLMs) that can lead to stereotypical preference. We mainly focus on gender stereotypes, but the method can be extended to other types of stereotype. We evaluate 7 PLMs on 9 types of cloze-style prompt with different information and base knowledge. The results indicate that PLMs show a certain amount of robustness against unrelated information and preference of shallow linguistic cues, such as word position and syntactic structure, but a lack of interpreting information by meaning. Such findings shed light on how to interact with PLMs in a neutral approach for both finetuning and evaluation.
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。
