REVIEW 20 cited by
Knowledge Unlearning for Mitigating Privacy Risks in 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
Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities. Previous work addressing privacy issues for language models has mostly focused on data preprocessing and differential privacy methods, both requiring re-training the underlying LM. We propose knowledge unlearning as an alternative method to reduce privacy risks for LMs post hoc. We show that simply performing gradient ascent on target token sequences is effective at forgetting them with little to no degradation of general language modeling performances for larger LMs; it sometimes even substantially improves the underlying LM with just a few iterations. We also find that sequential unlearning is better than trying to unlearn all the data at once and that unlearning is highly dependent on which kind of data (domain) is forgotten. By showing comparisons with a previous data preprocessing method and a decoding method known to mitigate privacy risks for LMs, we show that unlearning can give a stronger empirical privacy guarantee in scenarios where the data vulnerable to extraction attacks are known a priori while being much more efficient and robust. We release the code and dataset needed to replicate our results at https://github.com/joeljang/knowledge-unlearning.
Forward citations
Cited by 20 Pith papers
-
Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning
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.
-
Knowledge Beyond Language: Bridging the Gap in Multilingual Machine Unlearning Evaluation
New metrics KSS and KPS are introduced to evaluate multilingual machine unlearning quality and cross-language consistency in LLMs, addressing limitations of single-language evaluation protocols.
-
Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set
TC-UMIA is a population-level attack using pre- and post-unlearning predictions to infer membership across forget, retain, and unseen sets, revealing added privacy leakage to retained data.
-
Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set
Unlearning increases privacy leakage for the retain set, and a new tri-class membership inference attack distinguishes forget, retain, and unseen data using pre- and post-unlearning model outputs.
-
Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs
A special <|ino|> token trained into LLMs gates hazardous answers behind an assistant-side signal, beating unlearning and refusal baselines on safety-utility trade-offs.
-
Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning
TokenUnlearn identifies critical tokens via masking and entropy signals then applies hard selection or soft weighting to unlearn only those tokens, yielding better forgetting and retained utility than sequence-level b...
-
Jellyfish: Zero-Shot Federated Unlearning Scheme with Knowledge Disentanglement
Jellyfish enables zero-shot federated unlearning through synthetic proxy data generation, channel-restricted knowledge disentanglement, and a composite loss with repair to forget target data while retaining model utility.
-
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.
-
Anatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning
Fact popularity and training stage jointly change how unlearning behaves: popular facts are harder to erase, and a model fine-tuned on the evaluation data forgets more smoothly and retains more than a pretrained model.
-
Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking
FIA uses contrastive concept saliency and temporal-spatial neuron identification to build unified masks that erase multiple target concepts while preserving general generation quality in diffusion models.
-
Sparse Concept Anchoring for Interpretable and Controllable Neural Representations
Sparse Concept Anchoring biases neural latent spaces toward targeted concepts using under 0.1% labels per concept, enabling reversible steering via projection and permanent removal via weight ablation with minimal sid...
-
Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning
DiPO is a distribution-level unlearning method that constructs preference distributions from the model's own high-confidence logits and achieves state-of-the-art forget quality on TOFU while preserving utility.
-
Towards Evaluation for Real-World LLM Unlearning
DCUE evaluates LLM unlearning by comparing core-token confidence score distributions of the unlearned model and the original model, corrected by a validation set, using the Kolmogorov-Smirnov test.
-
TOFU: A Task of Fictitious Unlearning for LLMs
TOFU is a new benchmark with synthetic profiles and metrics demonstrating that existing unlearning algorithms for LLMs fail to achieve effective forgetting of targeted information.
-
Towards Scalable Lifelong Knowledge Editing with Selective Knowledge Suppression
LightEdit enables scalable lifelong knowledge editing in LLMs via selective knowledge retrieval and probability suppression during decoding, outperforming prior methods on ZSRE, Counterfact, and RIPE while reducing tr...
-
Module-Aware Parameter-Efficient Machine Unlearning on Transformers
MAPE-Unlearn uses Fisher-information-based scores and greedy search to select important heads and filters, then applies sparse unlearning updates, claiming improved efficacy-fidelity trade-offs on Transformers.
-
Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection
An LLM unlearning method that projects hidden states so harmful information is irreversibly removed while useful knowledge is preserved.
-
Revisiting the Past: Data Unlearning with Model State History
MSA performs data unlearning in LLMs by arithmetic operations on prior model checkpoints to remove targeted datapoint influence, with experiments showing competitive or better results than existing unlearning methods.
-
Hallucination of Multimodal Large Language Models: A Survey
The survey organizes causes of hallucinations in MLLMs, reviews evaluation benchmarks and metrics, and outlines mitigation approaches plus open questions.
-
Vision Language Model Helps Private Information De-Identification in Vision Data
VisShield with OPTIC dataset enables VLMs to localize and mask private text in vision data via instruction tuning for privacy preservation.
Discussion (0). Sign in to comment.