Offset Unlearning for Large Language Models
- URL: http://arxiv.org/abs/2404.11045v1
- Date: Wed, 17 Apr 2024 03:39:51 GMT
- Title: Offset Unlearning for Large Language Models
- Authors: James Y. Huang, Wenxuan Zhou, Fei Wang, Fred Morstatter, Sheng Zhang, Hoifung Poon, Muhao Chen,
- Abstract summary: Unlearning has emerged as a potential remedy for Large Language Models affected by problematic training data.
We propose $delta$-unlearning, an offset unlearning framework for black-box LLMs.
Experiments demonstrate that $delta$-unlearning can effectively unlearn target data while maintaining similar or even stronger performance on general out-of-forget-scope tasks.
- Score: 49.851093293780615
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Despite the strong capabilities of Large Language Models (LLMs) to acquire knowledge from their training corpora, the memorization of sensitive information in the corpora such as copyrighted, harmful, and private content has led to ethical and legal concerns. In response to these challenges, unlearning has emerged as a potential remedy for LLMs affected by problematic training data. However, previous unlearning techniques are either not applicable to black-box LLMs due to required access to model internal weights, or violate data protection principles by retaining sensitive data for inference-time correction. We propose $\delta$-unlearning, an offset unlearning framework for black-box LLMs. Instead of tuning the black-box LLM itself, $\delta$-unlearning learns the logit offset needed for unlearning by contrasting the logits from a pair of smaller models. Experiments demonstrate that $\delta$-unlearning can effectively unlearn target data while maintaining similar or even stronger performance on general out-of-forget-scope tasks. $\delta$-unlearning also effectively incorporates different unlearning algorithms, making our approach a versatile solution to adapting various existing unlearning algorithms to black-box LLMs.
Related papers
- Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs [18.629717934007513]
"SPlit, UNlearn, MerGE" (SPUNGE) is a framework that can be used with any unlearning method to amplify its effectiveness.
We empirically demonstrate that SPUNGE significantly improves the performance of two recent unlearning methods on state-of-the-art LLMs.
arXiv Detail & Related papers (2024-06-17T17:35:52Z) - SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning [30.25610464801255]
Large Language Models (LLMs) have highlighted the necessity of effective unlearning mechanisms to comply with data regulations and ethical AI practices.
While interest in studying LLM unlearning is growing, the impact of the choice for LLM unlearning remains unexplored.
We shed light on the significance of selection in LLM unlearning for the first time, establishing a clear connection between second-order optimization and influence unlearning.
arXiv Detail & Related papers (2024-04-28T16:31:32Z) - The Frontier of Data Erasure: Machine Unlearning for Large Language Models [56.26002631481726]
Large Language Models (LLMs) are foundational to AI advancements.
LLMs pose risks by potentially memorizing and disseminating sensitive, biased, or copyrighted information.
Machine unlearning emerges as a cutting-edge solution to mitigate these concerns.
arXiv Detail & Related papers (2024-03-23T09:26:15Z) - Unmemorization in Large Language Models via Self-Distillation and
Deliberate Imagination [58.36408867180233]
Large Language Models (LLMs) struggle with crucial issues of privacy violation and unwanted exposure of sensitive data.
We introduce a novel approach termed deliberate imagination in the context of LLM unlearning.
Our results demonstrate the usefulness of this approach across different models and sizes, and also with parameter-efficient fine-tuning.
arXiv Detail & Related papers (2024-02-15T16:21:14Z) - Rethinking Machine Unlearning for Large Language Models [85.92660644100582]
We explore machine unlearning in the domain of large language models (LLMs)
This initiative aims to eliminate undesirable data influence (e.g., sensitive or illegal information) and the associated model capabilities.
arXiv Detail & Related papers (2024-02-13T20:51:58Z) - Unlearnable Algorithms for In-context Learning [36.895152458323764]
In this paper, we focus on efficient unlearning methods for the task adaptation phase of a pretrained large language model.
We observe that an LLM's ability to do in-context learning for task adaptation allows for efficient exact unlearning of task adaptation training data.
We propose a new holistic measure of unlearning cost which accounts for varying inference costs.
arXiv Detail & Related papers (2024-02-01T16:43:04Z) - Unlearn What You Want to Forget: Efficient Unlearning for LLMs [92.51670143929056]
Large language models (LLMs) have achieved significant progress from pre-training on and memorizing a wide range of textual data.
This process might suffer from privacy issues and violations of data protection regulations.
We propose an efficient unlearning framework that could efficiently update LLMs without having to retrain the whole model after data removals.
arXiv Detail & Related papers (2023-10-31T03:35:59Z) - Transfer Learning without Knowing: Reprogramming Black-box Machine
Learning Models with Scarce Data and Limited Resources [78.72922528736011]
We propose a novel approach, black-box adversarial reprogramming (BAR), that repurposes a well-trained black-box machine learning model.
Using zeroth order optimization and multi-label mapping techniques, BAR can reprogram a black-box ML model solely based on its input-output responses.
BAR outperforms state-of-the-art methods and yields comparable performance to the vanilla adversarial reprogramming method.
arXiv Detail & Related papers (2020-07-17T01:52:34Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.