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.
Ask to Know More: Generating Counterfactual Explanations for Fake Claims
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Institute of Information Science, Academia Sinica（中央研究院信息科学研究所）；National Tsing Hua University（国立清华大学）；The Pennsylvania State University（宾夕法尼亚州立大学）；Institute of Information, Academia Sinica（中央研究院资讯研究所）
Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation
Technische Universität Berlin（柏林工业大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））；University of Marburg（马尔堡大学）；LMU Munich（慕尼黑大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心（MCML））；BIFOLD – Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所（BIFOLD））
CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation
Indian Institute of Technology, Madras（印度理工学院马德拉斯分校）；Paul G. Allen School of Computer Science & Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）；Allen Institute of Artificial Intelligence（艾伦人工智能研究所）；Meta AI
