Dissecting Fine-Tuning Unlearning in Large Language Models
Fine-tuning-based unlearning methods prevail for preventing targeted harmful, sensitive, or copyrighted information within large language models while preserving overall capabilities. However, the true effectiveness of these methods is unclear. In this work, we delve into the limitations of fine-tuning-based unlearning through activation patching and parameter restoration experiments. Our findings reveal that these methods alter the model's knowledge retrieval process, providing further evidence that they do not genuinely erase the problematic knowledge embedded in the model parameters. Instead, the coefficients generated by the MLP components in the model's final layer are the primary contributors to these seemingly positive unlearning effects, playing a crucial role in controlling the model's behaviors. Furthermore, behavioral tests demonstrate that this unlearning mechanism inevitably impacts the global behavior of the models, affecting unrelated knowledge or capabilities. The code is released at https://github.com/yihuaihong/Dissecting-FT-Unlearning.
Code (1)
Tasks
RetrievalMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Dissecting Language Models: Machine Unlearning via Selective Pruning
Understanding and shaping the behaviour of Large Language Models (LLMs) is increasingly important as applications become more powerful and more frequently adopted. This paper introduces a machine unlearning method specif…
Machine UnlearningInvariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
Machine unlearning offers a promising solution to privacy and safety concerns in large language models (LLMs) by selectively removing targeted knowledge while preserving utility. However, current methods are highly sensi…
Machine UnlearningMathSentiment AnalysisAnatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning
Machine Unlearning (MU) enables Large Language Models (LLMs) to remove unsafe or outdated information. However, existing work assumes that all facts are equally forgettable and largely ignores whether the forgotten knowl…
A General Framework to Enhance Fine-tuning-based LLM Unlearning
Unlearning has been proposed to remove copyrighted and privacy-sensitive data from Large Language Models (LLMs). Existing approaches primarily rely on fine-tuning-based methods, which can be categorized into gradient asc…
Guardrail Baselines for Unlearning in LLMs
Recent work has demonstrated that finetuning is a promising approach to 'unlearn' concepts from large language models. However, finetuning can be expensive, as it requires both generating a set of examples and running it…