REVIEW 8 cited by
UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI
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
Exact unlearning was first introduced as a privacy mechanism that allowed a user to retract their data from machine learning models on request. Shortly after, inexact schemes were proposed to mitigate the impractical costs associated with exact unlearning. More recently unlearning is often discussed as an approach for removal of impermissible knowledge i.e. knowledge that the model should not possess such as unlicensed copyrighted, inaccurate, or malicious information. The promise is that if the model does not have a certain malicious capability, then it cannot be used for the associated malicious purpose. In this paper we revisit the paradigm in which unlearning is used for in Large Language Models (LLMs) and highlight an underlying inconsistency arising from in-context learning. Unlearning can be an effective control mechanism for the training phase, yet it does not prevent the model from performing an impermissible act during inference. We introduce a concept of ununlearning, where unlearned knowledge gets reintroduced in-context, effectively rendering the model capable of behaving as if it knows the forgotten knowledge. As a result, we argue that content filtering for impermissible knowledge will be required and even exact unlearning schemes are not enough for effective content regulation. We discuss feasibility of ununlearning for modern LLMs and examine broader implications.
Forward citations
Cited by 8 Pith papers
-
How Context Attribution Handles What the Model Already Knows
Context attribution methods cannot disentangle in-context from in-weight knowledge and assign unfaithful scores under overlap; new metrics and WMDP-Cyber++ quantify the failure.
-
PPE-Bench: A Benchmark for Evaluating MLLM Unlearning under Private-Public Entanglement
Existing MLLM unlearning methods reduce private-attribute leakage on entangled images but substantially harm co-occurring public figures and landmarks, with private knowledge often re-emerging after public finetuning.
-
Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective
RULI is a per-sample, dual-objective inference attack that measures privacy leakage and unlearning efficacy, showing average-case evaluations understate privacy risk.
-
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.
-
Forget to Know, Remember to Use: Context-Aware Unlearning for Large Language Models
Unlearning methods suppress LLMs' ability to use forgotten facts even when the facts are given in context; adding a KL term that anchors contextual outputs to the original model restores this ability on the TOFU benchmark.
-
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.
-
Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods
Prepending a Hindi filler paragraph to WMDP-bio questions restores 57.3% accuracy in ELM-unlearned models, showing the unlearning is superficial output suppression rather than true knowledge removal.
-
A Survey on Generative Model Unlearning: Fundamentals, Taxonomy, Evaluation, and Future Direction
A survey and framework that categorizes generative model unlearning by point-wise versus concept-wise objectives, parameter-based versus non-parametric methods, and completeness/utility/efficiency evaluation.
Discussion (0). Continue with ORCID to comment.