如何精准删除语言模型中的特定内容？关键在选对要遗忘的数据集。
What to Forget in Unlearning? Forget Set Curation for Language Models
- 提出从海量文本中自动定位需遗忘内容的筛选方法
- 发现直接匹配关键词效果差，需考虑上下文语义与模型行为
- 适合关注模型可控性与数据安全的研究者
机器去学习旨在移除训练好的模型中特定数据或行为，而无需从头训练。然而多数评估假设待遗忘的样本已知。在真实语言模型部署中，请求方可能要求模型停止生成某首歌或某本书的内容，却不知道具体哪些片段、文档、引文或近似重复内容支撑了该行为。本文研究这一上游难题——遗忘集合筛选：将抑制请求映射到传给去学习算法的数据。提出CleanSlate基准，用于歌曲和书籍的原文输出抑制，包含模型特异性提取特征、基于内容的问答评估及能力保留测试。结果显示，自然词法和精确子串筛选器常导致抑制效果弱；而评估感知的筛选器虽能几乎完全抑制请求内容，却引发非请求内容的意外退化及模型依赖的能力损失。表明实际去学习不仅是给定遗忘集后的优化问题，所选遗忘数据本身决定了可去学习的程度以及伴随的损害。
原文摘要 · Abstract (English)
Machine unlearning aims to remove targeted data or behaviors from a trained model without retraining from scratch. Yet most evaluations assume that the examples to forget are already known. In realistic language-model deployments, a requester may ask a model to stop reproducing a song or book without knowing which spans, documents, quotations, or near-duplicates in a trillion-token corpus support that behavior. We study this missing upstream problem, forget set curation: mapping a suppression request to the data passed to an unlearning algorithm. We introduce CleanSlate, a benchmark for verbatim output suppression over songs and books, with model-specific extraction profiles, content-grounded QA, and capability-retention evaluations. CleanSlate exposes two failure modes. Natural lexical and exact-substring curators often yield forget sets that lead to weak suppression. An evaluation-aware curator suppresses requested continuations almost completely, but causes collateral regression on non-requested content and model-dependent capability loss. These results show that practical unlearning is not only an optimization problem once a forget set is given: the data chosen for forgetting determines both what can be unlearnt and what else is damaged.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。