arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.16835cs.CL
收藏

评估大语言模型中鲁棒遗忘的八种方法

Eight Methods to Evaluate Robust Unlearning in LLMs

University College London(伦敦大学学院);University of Maryland(马里兰大学);University of Bristol(布里斯托大学);MIT(麻省理工学院);MATS

Aengus Lynch, Phillip Guo, Aidan Ewart, Stephen Casper, Dylan Hadfield-Menell

AI总结:

本文针对大语言模型遗忘评估缺乏标准化的问题,以WHP模型为对象提出八种鲁棒性测试方法,发现其虽在Familiarity指标上表现良好,但仍存在知识可提取、问答性能未降、潜在知识保留及相关领域附带遗忘等问题,强调需要全面而非临时的遗忘评估体系。

摘要:

机器遗忘可用于从大语言模型(LLMs)中移除有害能力和记忆文本,但目前尚缺乏标准化的方法来严格评估其效果。在本文中,我们首先梳理了现有遗忘评估的技术与局限性。其次,我们对Eldan和Russinovich(2023)提出的“Who's Harry Potter”(WHP)模型应用了一套全面的测试,以检验其遗忘的鲁棒性和竞争力。虽然在使用Eldan和Russinovich的“Familiarity”指标评估时,WHP的遗忘表现出良好的泛化性,但我们发现:i)可以可靠地提取出高于基线水平的知识量;ii)WHP在哈利·波特问答任务上的表现与原始模型相当;iii)它对潜在知识的表征与原始模型具有可比性;iv)在相关领域存在附带遗忘。总体而言,我们的结果凸显了采用全面遗忘评估并避免临时性指标的重要性。

英文摘要:

Machine unlearning can be useful for removing harmful capabilities and memorized text from large language models (LLMs), but there are not yet standardized methods for rigorously evaluating it. In this paper, we first survey techniques and limitations of existing unlearning evaluations. Second, we apply a comprehensive set of tests for the robustness and competitiveness of unlearning in the "Who's Harry Potter" (WHP) model from Eldan and Russinovich (2023). While WHP's unlearning generalizes well when evaluated with the "Familiarity" metric from Eldan and Russinovich, we find i) higher-than-baseline amounts of knowledge can reliably be extracted, ii) WHP performs on par with the original model on Harry Potter Q&A tasks, iii) it represents latent knowledge comparably to the original model, and iv) there is collateral unlearning in related domains. Overall, our results highlight the importance of comprehensive unlearning evaluation that avoids ad-hoc metrics.

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。

↑