反学习不是删除：调查机器反学习在大语言模型中的可逆性
Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
AI总结：
研究揭示大语言模型反学习的可逆性问题，提出表示层面分析框架，通过PCA相似度、CKA和Fisher信息等指标评估表示漂移，发现四种遗忘模式，指出数据来源影响重学效率，揭示不可逆遗忘的挑战。
摘要：
在大语言模型（LLMs）中，反学习旨在移除指定数据，但其效果通常通过任务级指标如准确率和困惑度评估。我们证明这些指标可能误导，因为模型似乎遗忘，但通过最小微调即可恢复原始行为。这种可逆性表明信息被抑制而非真正删除。为填补这一评估空白，我们引入表示层面分析框架。我们的工具包包括PCA相似度和位移、中心核对齐（CKA）和Fisher信息，辅以均值PCA距离作为总结指标，用于衡量表示漂移。在多种反学习方法、数据领域和LLMs上应用此框架，我们识别出四种基于可逆性和灾难性程度的遗忘模式。我们比较了恢复策略，发现重学效率依赖于数据来源。我们还发现不可逆、非灾难性遗忘异常困难。通过探测反学习极限，我们识别出一个看似不可逆的目标遗忘案例，为更稳健的擦除算法提供见解。总体而言，我们的发现揭示了当前评估的差距，并建立了可信反学习的表示层面基础。
英文摘要：
Unlearning in large language models (LLMs) aims to remove specified data, but its efficacy is typically assessed with task-level metrics like accuracy and perplexity. We show that these metrics can be misleading, as models can appear to forget while their original behavior is easily restored through minimal fine-tuning. This \emph{reversibility} suggests that information is merely suppressed, not genuinely erased. To address this critical evaluation gap, we introduce a \emph{representation-level analysis framework}. Our toolkit comprises PCA similarity and shift, centered kernel alignment (CKA), and Fisher information, complemented by a summary metric, the mean PCA distance, to measure representational drift. Applying this framework across multiple unlearning methods, data domains, and LLMs, we identify four distinct forgetting regimes based on their \emph{reversibility} and \emph{catastrophicity}. We compare recovery strategies and show that relearning efficiency relies on the data source. We also find that irreversible, non-catastrophic forgetting is exceptionally challenging. By probing unlearning limits, we identify a case of seemingly irreversible, targeted forgetting, offering insights for more robust erasure algorithms. Overall, our findings expose a gap in current evaluation and establish a representation-level foundation for trustworthy unlearning.
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。
