用反样本让大模型遗忘特定知识，又不伤及其他内容。
UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs
- 用误导性推理生成反样本，反向干扰模型记忆
- 可精准删除特定关联，不影响其他知识
- 为隐私保护和模型可控修改提供新思路
机器学习的核心是训练数据、模型和损失函数。类比地，未学习（unlearning）或可通过反数据样本（反样本）、未学习方法和反向损失函数实现。尽管已有研究探索了未学习方法和反向损失函数，但反样本的潜力仍待挖掘。本文提出 UnSTAR：面向大语言模型的自教式反样本推理未学习方法。贡献有三：首先，提出反样本驱动的未学习新范式；其次，利用误导性推理生成反样本，帮助逆转模型已学关联并加速未学习过程；第三，实现细粒度的目标化未学习，可选择性移除特定知识而不影响相关知识——这是此前工作无法实现的。实验表明，反样本为大模型提供了一种高效、精准的未学习策略，为隐私保护机器学习和模型修改开辟了新路径。
原文摘要 · Abstract (English)
The key components of machine learning are data samples for training, model for learning patterns, and loss function for optimizing accuracy. Analogously, unlearning can potentially be achieved through anti-data samples (or anti-samples), unlearning method, and reversed loss function. While prior research has explored unlearning methods and reversed loss functions, the potential of anti-samples remains largely untapped. In this paper, we introduce UnSTAR: Unlearning with Self-Taught Anti-Sample Reasoning for large language models (LLMs). Our contributions are threefold; first, we propose a novel concept of anti-sample-induced unlearning; second, we generate anti-samples by leveraging misleading rationales, which help reverse learned associations and accelerate the unlearning process; and third, we enable fine-grained targeted unlearning, allowing for the selective removal of specific associations without impacting related knowledge - something not achievable by previous works. Results demonstrate that anti-samples offer an efficient, targeted unlearning strategy for LLMs, opening new avenues for privacy-preserving machine learning and model modification.
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。