REVIEW 25 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 25 Pith papers
-
The Space Complexity of Learning-Unlearning Algorithms
The space complexity of machine unlearning for realizability testing is characterized by eluder dimension (central lower bound), star number (ticketed upper bound), and hollow star number (bounded deletions), separati...
-
System-Aware Unlearning Algorithms: Use Lesser, Forget Faster
The paper introduces system-aware unlearning and gives the first exact unlearning algorithm for linear classification that stores a sublinear-size core set instead of the entire dataset.
-
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.
-
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.
-
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.
-
Enhancing Safe and Controllable Protein Generation via Knowledge Preference Optimization
A knowledge-graph-guided preference optimization framework that fine-tunes protein language models to generate fewer sequences similar to known harmful proteins.
-
Towards a Principled Evaluation of Knowledge Editors
The choice of evaluation metric, generation length, and edit batch size changes the ranking of knowledge editors, and exact string matching produces false positives.
-
Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs
A new method, Partial Model Collapse, iteratively fine-tunes an LLM on its own self-generated responses to conditionally collapse its output distribution on forget queries, removing private answers without the true la...
-
Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs
Unlearning in LLMs leaves detectable 'fingerprints' that let a simple classifier distinguish an unlearned model from its original, even on unrelated prompts.
-
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.
-
Understanding and Mitigating Cross-lingual Privacy Leakage via Language-specific and Universal Privacy Neurons
Cross-lingual privacy leakage in LLMs is driven by a mix of language-universal and language-specific neurons, and deactivating those neurons lowers measured leakage by 23.3% to 31.6%.
-
A Lightweight Method to Disrupt Memorized Sequences in LLM
A decoding-time intervention that substitutes a small model's probabilities for common function words into a large model's output reduces exact training-data recall by up to 10x with minimal measured quality loss.
-
Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning
SSU combines task-vector negation, random-label loss, and weight saliency to forget copyrighted books sequentially while retaining more general language ability than existing baselines.
-
SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs?
SEUF restricts MoE LLM unlearning to the top-1 most relevant expert and adds a router anchor loss, improving utility by up to 35% while keeping forget efficacy roughly comparable.
-
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.
-
Automating Evaluation of Diffusion Model Unlearning with (Vision-) Language Model World Knowledge
A new evaluation tool uses (vision-)language model world knowledge to rank nearby concepts and craft adversarial prompts, showing that diffusion unlearning is incomplete and that semantic similarity correlates with co...
-
Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
Adding sharpness-aware minimization to NPO unlearning slows relearning attacks on WMDP and MUSE benchmarks.
-
The Dual-use Dilemma in LLMs: Do Empowering Ethical Capacities Make a Degraded Utility?
A DPO-based alignment method with a balanced mixture of legal and illegal chemistry prompts improves combined safety and utility scores, but its benchmark shares training compounds and its hyperparameters are tuned on...
-
Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning
Standard random-data LLM unlearning evaluations understate privacy leakage for minority data, as shown by canary and real rare-PII experiments across three datasets and two models.
-
Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models
Step-by-step reasoning prompts can recover purportedly erased facts from unlearned LLMs, but the paper's quantitative evidence is internally inconsistent.
-
Lifting Data-Tracing Machine Unlearning to Knowledge-Tracing for Foundation Models
A position paper urging a shift from data-tracing to knowledge-tracing machine unlearning for foundation models, supported by a CLIP case study that shows current methods struggle to generalize.
-
UCD: Unlearning in LLMs via Contrastive Decoding
UCD steers an LLM away from forget-set content at inference time by mixing in the difference between forget-tuned and retain-tuned small models.
-
iShumei-Chinchunmei at SemEval-2025 Task 4: A balanced forgetting and retention multi-task framework using effective unlearning loss
The authors propose Effective Unlearning Loss, the inverse of the standard next-token prediction loss, within a multi-task framework, and report a 5th-place finish at SemEval-2025 Task 4.
Discussion (0). Continue with ORCID to comment.