REVIEW 9 cited by
A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
This study investigates the machine unlearning techniques within the context of large language models (LLMs), referred to as \textit{LLM unlearning}. LLM unlearning offers a principled approach to removing the influence of undesirable data (e.g., sensitive or illegal information) from LLMs, while preserving their overall utility without requiring full retraining. Despite growing research interest, there is no comprehensive survey that systematically organizes existing work and distills key insights; here, we aim to bridge this gap. We begin by introducing the definition and the paradigms of LLM unlearning, followed by a comprehensive taxonomy of existing unlearning studies. Next, we categorize current unlearning approaches, summarizing their strengths and limitations. Additionally, we review evaluation metrics and benchmarks, providing a structured overview of current assessment methodologies. Finally, we outline promising directions for future research, highlighting key challenges and opportunities in the field.
Forward citations
Cited by 9 Pith papers
-
Gradient Concentration, Not Weight Saliency, Explains Representation-Level Class Unlearning
In class unlearning on CIFAR-10/100 with ResNet-18, the identity of saliency-selected weights does not affect representation-level recovery; late-layer gradient concentration and representation geometry drive the outcome.
-
One Modality to Forget Them All: Enhancing Cross-Modal Unlearning in Vision-Language Models
Cross-modal unlearning transfer in vision-language models is asymmetric, architecture-dependent, and shallow under typographic attacks; influence-guided block selection reduces the measured gap.
-
Anatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning
SFT models forget facts more stably than pretrained models, with 10-50% higher retention of unrelated knowledge when using the DUET benchmark of 28.6k Wikidata triplets.
-
LLM Unlearning Should Be Form-Independent
Existing LLM unlearning is form-dependent; the new ORT benchmark measures this, and the training-free ROCR edit reduces it by redirecting concept representations.
-
Model Unlearning via Sparse Autoencoder Subspace Guided Projections
SSPU uses SAE-derived subspaces to guide weight updates, lowering WMDP-Cyber accuracy by 3.22% more than RMU while largely preserving MMLU, TruthfulQA, and GSM8K performance.
-
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
A system-first taxonomy and literature synthesis of multimodal unlearning across vision, language, video, and audio, with datasets, benchmarks, metrics, applications, and open challenges.
-
BalDRO: A Distributionally Robust Optimization based Framework for Large Language Model Unlearning
BalDRO makes LLM unlearning more balanced by updating against a worst-case-weighted forget distribution, improving forget quality on TOFU/MUSE at stable utility.
-
VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration
A new benchmark, VSCBench, measures oversafety and undersafety in vision-language models and shows that most models, including proprietary ones, are miscalibrated on at least one safety dimension.
-
Get Experience from Practice: LLM Agents with Record & Replay
AgentRR is a proposed paradigm that records agent traces, generalizes them into multi-level experiences, and replays them under safety checks to make LLM agents cheaper, faster, and more reliable.
Discussion (0). Continue with ORCID to comment.