pith. sign in

arxiv: 2402.08787 · v6 · pith:OKQU26RAnew · submitted 2024-02-13 · 💻 cs.LG · cs.CL

Rethinking Machine Unlearning for Large Language Models

classification 💻 cs.LG cs.CL
keywords unlearningllmsmodelapplicationsassessmentessentialexploreinfluence
0
0 comments X
read the original abstract

We explore machine unlearning (MU) in the domain of large language models (LLMs), referred to as LLM unlearning. This initiative aims to eliminate undesirable data influence (e.g., sensitive or illegal information) and the associated model capabilities, while maintaining the integrity of essential knowledge generation and not affecting causally unrelated information. We envision LLM unlearning becoming a pivotal element in the life-cycle management of LLMs, potentially standing as an essential foundation for developing generative AI that is not only safe, secure, and trustworthy, but also resource-efficient without the need of full retraining. We navigate the unlearning landscape in LLMs from conceptual formulation, methodologies, metrics, and applications. In particular, we highlight the often-overlooked aspects of existing LLM unlearning research, e.g., unlearning scope, data-model interaction, and multifaceted efficacy assessment. We also draw connections between LLM unlearning and related areas such as model editing, influence functions, model explanation, adversarial training, and reinforcement learning. Furthermore, we outline an effective assessment framework for LLM unlearning and explore its applications in copyright and privacy safeguards and sociotechnical harm reduction.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning

    cs.LG 2024-04 conditional novelty 8.0

    NPO enables stable unlearning of 50%+ training data in LLMs on TOFU by making collapse exponentially slower than gradient ascent, preserving sensible outputs where prior methods fail.

  2. TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation

    cs.IR 2026-06 unverdicted novelty 7.0

    TRACER uses token reassignment for concept-related items plus a coherence regularizer to unlearn specific concepts in generative recommendation while preserving utility better than baselines.

  3. RepSelect: Robust LLM Unlearning via Representation Selectivity

    cs.CL 2026-06 unverdicted novelty 6.0

    RepSelect isolates forget-set-specific representations via gradient PCA collapse to achieve 4-50x better post-relearning robustness than baselines across multiple models and forget categories.

  4. Model Unlearning Objectives Vary for Distinct Language Functions

    cs.CL 2026-05 unverdicted novelty 6.0

    Unlearning objectives should be tailored to distinct language functions, with a meta-learned RMU variant for dangerous knowledge and a multi-layer probe objective for toxicity, yielding strong results on four 7-8B models.

  5. Representation-Guided Parameter-Efficient LLM Unlearning

    cs.CL 2026-04 unverdicted novelty 6.0

    REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.

  6. Hey, That's My Data! Token-Only Dataset Inference in Large Language Models

    cs.CL 2025-06 unverdicted novelty 6.0

    CatShift detects training data membership in LLMs by comparing output shifts induced by fine-tuning on member versus non-member data, relying on catastrophic forgetting without requiring logit access.

  7. Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents

    cs.CR 2026-06 unverdicted novelty 5.0

    A data-centric survey finds that only information-flow control covers compositional and cross-session leakage in LLM agents and that no single benchmark tests an agent across all its data surfaces under one policy.

  8. EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget

    cs.CL 2025-10 unverdicted novelty 5.0

    EEPO uses sample-then-forget rollouts with adaptive unlearning to boost exploration in RLVR, delivering relative gains of 24.3% on Qwen2.5-3B, 33.0% on Llama3.2-3B-Instruct, and 10.4% on Qwen3-8B-Base over GRPO across...