Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective
This paper investigates Who's Harry Potter (WHP), a pioneering yet insufficiently understood method for LLM unlearning. We explore it in two steps. First, we introduce a new task of LLM targeted unlearning, where given an unlearning target (e.g., a person) and some unlearning documents, we aim to unlearn only the information about the target, rather than everything in the unlearning documents. We further argue that a successful unlearning should satisfy criteria such as not outputting gibberish, not fabricating facts about the unlearning target, and not releasing factual information under jailbreak attacks. Second, we construct a causal intervention framework for targeted unlearning, where the knowledge of the unlearning target is modeled as a confounder between LLM input and output, and the unlearning process as a deconfounding process. This framework justifies and extends WHP, deriving a simple unlearning algorithm that includes WHP as a special case. Experiments on existing and new datasets show that our approach, without explicitly optimizing for the aforementioned criteria, achieves competitive performance in all of them. Our code is available at https://github.com/UCSB-NLP-Chang/causal_unlearn.git.
Code (1)
Similar Papers 제목 키워드 기반
Harry Potter is Still Here! Probing Knowledge Leakage in Targeted Unlearned Large Language Models via Automated Adversarial Prompting
This work presents LURK (Latent UnleaRned Knowledge), a novel framework that probes for hidden retained knowledge in unlearned LLMs through adversarial suffix prompting. LURK automatically generates adversarial prompt su…
DiagnosticJogging the Memory of Unlearned LLMs Through Targeted Relearning Attacks
Machine unlearning is a promising approach to mitigate undesirable memorization of training data in LLMs. However, in this work we show that existing approaches for unlearning in LLMs are surprisingly susceptible to a si…
ArticlesMachine UnlearningMemorizationEight Methods to Evaluate Robust Unlearning in LLMs
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 su…
Machine UnlearningWho's Harry Potter? Approximate Unlearning in LLMs
Large language models (LLMs) are trained on massive internet corpora that often contain copyrighted content. This poses legal and ethical challenges for the developers and users of these models, as well as the original a…
ARCGPUHellaSwagLanguage Modelling+1OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models
Large language models (LLMs) trained over extensive corpora risk memorizing sensitive, copyrighted, or toxic content. To address this, we propose OBLIVIATE, a robust unlearning framework that removes targeted data while …
Machine UnlearningMemorization