Rethinking Entity-level Unlearning for Large Language Models
- URL: http://arxiv.org/abs/2406.15796v1
- Date: Sat, 22 Jun 2024 09:40:07 GMT
- Title: Rethinking Entity-level Unlearning for Large Language Models
- Authors: Weitao Ma, Xiaocheng Feng, Weihong Zhong, Lei Huang, Yangfan Ye, Bing Qin,
- Abstract summary: We propose a novel task of entity-level unlearning, where the entity-related knowledge within the target model is supposed to be entirely erased.
Experiments reveal that current unlearning algorithms struggle to achieve effective entity-level unlearning.
- Score: 28.708701013154993
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large language model unlearning has gained increasing attention due to its potential to mitigate security and privacy concerns. Current research predominantly focuses on Instance-level unlearning, specifically aiming at forgetting predefined instances of sensitive content. However, a notable gap still exists in exploring the deletion of complete entity-related information, which is crucial in many real-world scenarios, such as copyright protection. To this end, we propose a novel task of Entity-level unlearning, where the entity-related knowledge within the target model is supposed to be entirely erased. Given the challenge of practically accessing all entity-related knowledge within a model, we begin by simulating entity-level unlearning scenarios through fine-tuning models to introduce pseudo entities. Following this, we develop baseline methods inspired by trending unlearning techniques and conduct a detailed comparison of their effectiveness in this task. Extensive experiments reveal that current unlearning algorithms struggle to achieve effective entity-level unlearning. Additionally, our analyses further indicate that entity-related knowledge injected through fine-tuning is more susceptible than original entities from pre-training during unlearning, highlighting the necessity for more thorough pseudo-entity injection methods to make them closer to pre-trained knowledge.
Related papers
- Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models [79.28821338925947]
Domain-Class Incremental Learning is a realistic but challenging continual learning scenario.
To handle these diverse tasks, pre-trained Vision-Language Models (VLMs) are introduced for their strong generalizability.
This incurs a new problem: the knowledge encoded in the pre-trained VLMs may be disturbed when adapting to new tasks, compromising their inherent zero-shot ability.
Existing methods tackle it by tuning VLMs with knowledge distillation on extra datasets, which demands heavy overhead.
We propose the Distribution-aware Interference-free Knowledge Integration (DIKI) framework, retaining pre-trained knowledge of
arXiv Detail & Related papers (2024-07-07T12:19:37Z) - Towards Federated Domain Unlearning: Verification Methodologies and Challenges [34.9987941096371]
We present the first comprehensive empirical study on Federated Domain Unlearning.
Our findings reveal that unlearning disproportionately affects the model's deeper layers.
We propose novel evaluation methodologies tailored for Federated Domain Unlearning.
arXiv Detail & Related papers (2024-06-05T09:05:55Z) - An Information Theoretic Approach to Machine Unlearning [45.600917449314444]
Key challenge in unlearning is forgetting the necessary data in a timely manner, while preserving model performance.
In this work, we address the zero-shot unlearning scenario, whereby an unlearning algorithm must be able to remove data given only a trained model and the data to be forgotten.
We derive a simple but principled zero-shot unlearning method based on the geometry of the model.
arXiv Detail & Related papers (2024-02-02T13:33:30Z) - A Comprehensive Study on Model Initialization Techniques Ensuring
Efficient Federated Learning [0.0]
Federated learning(FL) has emerged as a promising paradigm for training machine learning models in a distributed and privacy-preserving manner.
The choice of methods used for models plays a crucial role in the performance, convergence speed, communication efficiency, privacy guarantees of federated learning systems.
Our research meticulously compares, categorizes, and delineates the merits and demerits of each technique, examining their applicability across diverse FL scenarios.
arXiv Detail & Related papers (2023-10-31T23:26:58Z) - Large Language Models with Controllable Working Memory [64.71038763708161]
Large language models (LLMs) have led to a series of breakthroughs in natural language processing (NLP)
What further sets these models apart is the massive amounts of world knowledge they internalize during pretraining.
How the model's world knowledge interacts with the factual information presented in the context remains under explored.
arXiv Detail & Related papers (2022-11-09T18:58:29Z) - Learnware: Small Models Do Big [69.88234743773113]
The prevailing big model paradigm, which has achieved impressive results in natural language processing and computer vision applications, has not yet addressed those issues, whereas becoming a serious source of carbon emissions.
This article offers an overview of the learnware paradigm, which attempts to enable users not need to build machine learning models from scratch, with the hope of reusing small models to do things even beyond their original purposes.
arXiv Detail & Related papers (2022-10-07T15:55:52Z) - Effective Few-Shot Named Entity Linking by Meta-Learning [34.70028855572534]
We propose a novel weak supervision strategy to generate non-trivial synthetic entity-mention pairs.
We also design a meta-learning mechanism to assign different weights to each synthetic entity-mention pair automatically.
Experiments on real-world datasets show that the proposed method can extensively improve the state-of-the-art few-shot entity linking model.
arXiv Detail & Related papers (2022-07-12T03:23:02Z) - Vertical Machine Unlearning: Selectively Removing Sensitive Information
From Latent Feature Space [21.8933559159369]
We investigate a vertical unlearning mode, aiming at removing only sensitive information from latent feature space.
We introduce intuitive and formal definitions for this unlearning and show its relationship with existing horizontal unlearning.
We propose an approximation with an upper bound to estimate it, with rigorous theoretical analysis.
arXiv Detail & Related papers (2022-02-27T05:25:15Z) - What Makes Good Contrastive Learning on Small-Scale Wearable-based
Tasks? [59.51457877578138]
We study contrastive learning on the wearable-based activity recognition task.
This paper presents an open-source PyTorch library textttCL-HAR, which can serve as a practical tool for researchers.
arXiv Detail & Related papers (2022-02-12T06:10:15Z) - Knowledge-driven Active Learning [70.37119719069499]
Active learning strategies aim at minimizing the amount of labelled data required to train a Deep Learning model.
Most active strategies are based on uncertain sample selection, and even often restricted to samples lying close to the decision boundary.
Here we propose to take into consideration common domain-knowledge and enable non-expert users to train a model with fewer samples.
arXiv Detail & Related papers (2021-10-15T06:11:53Z) - Goal-Aware Prediction: Learning to Model What Matters [105.43098326577434]
One of the fundamental challenges in using a learned forward dynamics model is the mismatch between the objective of the learned model and that of the downstream planner or policy.
We propose to direct prediction towards task relevant information, enabling the model to be aware of the current task and encouraging it to only model relevant quantities of the state space.
We find that our method more effectively models the relevant parts of the scene conditioned on the goal, and as a result outperforms standard task-agnostic dynamics models and model-free reinforcement learning.
arXiv Detail & Related papers (2020-07-14T16:42:59Z)
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.