Unlearning in LLMs: Methods, Evaluation, and Open Challenges
Large language models (LLMs) have achieved remarkable success across natural language processing tasks, yet their widespread deployment raises pressing concerns around privacy, copyright, security, and bias. Machine unlearning has emerged as a promising paradigm for selectively removing knowledge or data from trained models without full retraining. In this survey, we provide a structured overview of unlearning methods for LLMs, categorizing existing approaches into data-centric, parameter-centric, architecture-centric, hybrid, and other strategies. We also review the evaluation ecosystem, including benchmarks, metrics, and datasets designed to measure forgetting effectiveness, knowledge retention, and robustness. Finally, we outline key challenges and open problems, such as scalable efficiency, formal guarantees, cross-language and multimodal unlearning, and robustness against adversarial relearning. By synthesizing current progress and highlighting open directions, this paper aims to serve as a roadmap for developing reliable and responsible unlearning techniques in large language models.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics
Robust unlearning is crucial for safely deploying large language models (LLMs) in environments where data privacy, model safety, and regulatory compliance must be ensured. Yet the task is inherently challenging, partly d…
BenchmarkingKnowledge Unlearning for LLMs: Tasks, Methods, and Challenges
In recent years, large language models (LLMs) have spurred a new research paradigm in natural language processing. Despite their excellent capability in knowledge-based question answering and reasoning, their potential t…
In-Context LearningMachine UnlearningQuestion AnsweringSurveyTool Unlearning for Tool-Augmented LLMs
Tool-augmented large language models (LLMs) are often trained on datasets of query-response pairs, which embed the ability to use tools or APIs directly into the parametric knowledge of LLMs. Tool-augmented LLMs need the…
Inference AttackMembership Inference AttackCLEAR: Character Unlearning in Textual and Visual Modalities
Machine Unlearning (MU) is critical for enhancing privacy and security in deep learning models, particularly in large multimodal language models (MLLMs), by removing specific private or hazardous information. While MU ha…
Machine UnlearningUnlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
Unlearning in large language models (LLMs) is intended to remove the influence of specific data, yet current evaluations rely heavily on token-level metrics such as accuracy and perplexity. We show that these metrics can…
DiagnosticMachine UnlearningMath