Interventions targeting the representation space of language models (LMs) have emerged as an effective means to influence model behavior. Such methods are employed, for example, to eliminate or alter the encoding of demographic information such as gender within the model's representations and, in so doing, create a counterfactual representation. However, because the intervention operates within the representation space, understanding precisely what aspects of the text it modifies poses a challenge. In this paper, we give a method to convert representation counterfactuals into string counterfactuals. We demonstrate that this approach enables us to analyze the linguistic alterations corresponding to a given representation space intervention and to interpret the features utilized to encode a specific concept. Moreover, the resulting counterfactuals can be used to mitigate bias in classification through data augmentation.

翻译：针对语言模型表征空间进行干预已成为影响模型行为的有效手段。此类方法被用于在模型表征中消除或改变诸如性别等人口统计学信息的编码，进而创建反事实表征。然而，由于干预作用于表征空间，准确理解其修改了文本的哪些具体方面构成了一项挑战。本文提出了一种将表征反事实转化为字符串反事实的方法。我们证明，该方法能够分析对应于特定表征空间干预的语言改变，并解读用于编码特定概念的特征。此外，生成的反事实可通过数据增强用于缓解分类中的偏差。