Unveiling Entity-Level Unlearning for Large Language Models: A Comprehensive Analysis

• URL: http://arxiv.org/abs/2406.15796v4
• Date: Fri, 18 Oct 2024 02:00:57 GMT
• Title: Unveiling Entity-Level Unlearning for Large Language Models: A Comprehensive Analysis
• Authors: Weitao Ma, Xiaocheng Feng, Weihong Zhong, Lei Huang, Yangfan Ye, Xiachong Feng, Bing Qin,
• Abstract summary: Large language model unlearning has garnered increasing attention due to its potential to address security and privacy concerns. Much of this research has concentrated on instance-level unlearning, specifically targeting the removal of predefined instances containing sensitive content. We propose a novel task of entity-level unlearning, which aims to erase entity-related knowledge from the target model completely.
• Score: 32.455702022397666
• License:
• Abstract: Large language model unlearning has garnered increasing attention due to its potential to address security and privacy concerns, leading to extensive research in the field. However, much of this research has concentrated on instance-level unlearning, specifically targeting the removal of predefined instances containing sensitive content. This focus has left a significant gap in the exploration of full entity-level unlearning, which is critical in real-world scenarios such as copyright protection. To this end, we propose a novel task of Entity-level unlearning, which aims to erase entity-related knowledge from the target model completely. To thoroughly investigate this task, we systematically evaluate trending unlearning algorithms, revealing that current methods struggle to achieve effective entity-level unlearning. Then, we further explore the factors that influence the performance of the unlearning algorithms, identifying that knowledge coverage and the size of the forget set play pivotal roles. Notably, our analysis also uncovers that entities introduced through fine-tuning are more vulnerable to unlearning than pre-trained entities. These findings collectively offer valuable insights for advancing entity-level unlearning for LLMs.

Related papers

• Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset [94.13848736705575]
  We introduce Facial Identity Unlearning Benchmark (FIUBench), a novel VLM unlearning benchmark designed to robustly evaluate the effectiveness of unlearning algorithms. We apply a two-stage evaluation pipeline that is designed to precisely control the sources of information and their exposure levels. Through the evaluation of four baseline VLM unlearning algorithms within FIUBench, we find that all methods remain limited in their unlearning performance.
  arXiv  Detail & Related papers  (2024-11-05T23:26:10Z)
• Aggregation Artifacts in Subjective Tasks Collapse Large Language Models' Posteriors [74.04775677110179]
  In-context Learning (ICL) has become the primary method for performing natural language tasks with Large Language Models (LLMs) In this work, we examine whether this is the result of the aggregation used in corresponding datasets, where trying to combine low-agreement, disparate annotations might lead to annotation artifacts that create detrimental noise in the prompt. Our results indicate that aggregation is a confounding factor in the modeling of subjective tasks, and advocate focusing on modeling individuals instead.
  arXiv  Detail & Related papers  (2024-10-17T17:16:00Z)
• CodeUnlearn: Amortized Zero-Shot Machine Unlearning in Language Models Using Discrete Concept [5.345828824625758]
  We propose a novel amortized unlearning approach using codebook features and Sparse Autoencoders (SAEs) By leveraging a bottleneck to decompose the activation space and regulate information flow, our method efficiently unlearns targeted information while preserving the model's performance on unrelated data.
  arXiv  Detail & Related papers  (2024-10-08T10:26:22Z)
• Federated Learning driven Large Language Models for Swarm Intelligence: A Survey [2.769238399659845]
  Federated learning (FL) offers a compelling framework for training large language models (LLMs) We focus on machine unlearning, a crucial aspect for complying with privacy regulations like the Right to be Forgotten. We explore various strategies that enable effective unlearning, such as perturbation techniques, model decomposition, and incremental learning.
  arXiv  Detail & Related papers  (2024-06-14T08:40:58Z)
• Fusing Domain-Specific Content from Large Language Models into Knowledge Graphs for Enhanced Zero Shot Object State Classification [0.8232137862012223]
  This study investigates the potential of Large Language Models (LLMs) in generating and providing domain-specific information. To achieve this, an LLM is integrated into a pipeline that utilizes Knowledge Graphs and pre-trained semantic vectors. Our findings reveal that the integration of LLM-based embeddings, in combination with general-purpose pre-trained embeddings, leads to substantial performance improvements.
  arXiv  Detail & Related papers  (2024-03-18T18:08:44Z)
• 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)
• A Survey of Label-Efficient Deep Learning for 3D Point Clouds [109.07889215814589]
  This paper presents the first comprehensive survey of label-efficient learning of point clouds. We propose a taxonomy that organizes label-efficient learning methods based on the data prerequisites provided by different types of labels. For each approach, we outline the problem setup and provide an extensive literature review that showcases relevant progress and challenges.
  arXiv  Detail & Related papers  (2023-05-31T12:54:51Z)
• 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)
• The Value of Information When Deciding What to Learn [21.945359614094503]
  This work builds upon the seminal design principle of information-directed sampling (Russo & Van Roy, 2014) We offer new insights into learning targets from the literature on rate-distortion theory before turning to empirical results that confirm the value of information when deciding what to learn.
  arXiv  Detail & Related papers  (2021-10-26T19:23:12Z)
• Incremental Object Detection via Meta-Learning [77.55310507917012]
  We propose a meta-learning approach that learns to reshape model gradients, such that information across incremental tasks is optimally shared. In comparison to existing meta-learning methods, our approach is task-agnostic, allows incremental addition of new-classes and scales to high-capacity models for object detection.
  arXiv  Detail & Related papers  (2020-03-17T13:40:00Z)

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.