paper-with-me

Papers

Dissecting Fine-Tuning Unlearning in Large Language Models

2024-10-09 · Yihuai Hong, Yuelin Zou, Lijie Hu, Ziqian Zeng, Di Wang, Haiqin Yang

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.

📄 PDF Abstract BibTeX arXiv:2410.06606

Code (1)

yihuaihong/dissecting-ft-unlearning 공식 구현 pytorch

Tasks

Retrieval

Methods 이 논문이 사용한 방법론

Patching Activation patching studies the model's computation by altering its latent representations, the token embeddings in transformer-based language models, during the inference process

Similar Papers 제목 키워드 기반

Dissecting Language Models: Machine Unlearning via Selective Pruning

2024-03-02 · Nicholas Pochinkov, Nandi Schoots

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 Unlearning

Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning

2025-06-02 · Changsheng Wang, Yihua Zhang, Jinghan Jia, Parikshit Ram 외

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 Analysis

Anatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning

2026-02-23 · Anna Borisiuk, Andrey Savchenko, Alexander Panchenko, Elena Tutubalina arxiv

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

2025-02-25 · Jie Ren, Zhenwei Dai, Xianfeng Tang, Jingying Zeng 외

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

2024-03-05 · Pratiksha Thaker, Yash Maurya, Shengyuan Hu, Zhiwei Steven Wu 외

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…