REVIEW 4 cited by
Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference
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
As Large Language Models (LLMs) demonstrate extensive capability in learning from documents, LLM unlearning becomes an increasingly important research area to address concerns of LLMs in terms of privacy, copyright, etc. A conventional LLM unlearning task typically involves two goals: (1) The target LLM should forget the knowledge in the specified forget documents, and (2) it should retain the other knowledge that the LLM possesses, for which we assume access to a small number of retain documents. To achieve both goals, a mainstream class of LLM unlearning methods introduces an optimization framework with a combination of two objectives - maximizing the prediction loss on the forget documents while minimizing that on the retain documents, which suffers from two challenges, degenerated output and catastrophic forgetting. In this paper, we propose a novel unlearning framework called Unlearning from Logit Difference (ULD), which introduces an assistant LLM that aims to achieve the opposite of the unlearning goals: remembering the forget documents and forgetting the retain knowledge. ULD then derives the unlearned LLM by computing the logit difference between the target and the assistant LLMs. We show that such reversed objectives would naturally resolve both aforementioned challenges while significantly improving the training efficiency. Extensive experiments demonstrate that our method efficiently achieves the intended forgetting while preserving the LLM's overall capabilities, reducing training time by more than threefold. Notably, our method loses 0% of model utility on the ToFU benchmark, whereas baseline methods may sacrifice 17% of utility on average to achieve comparable forget quality. Our code will be publicly available at https://github.com/UCSB-NLP-Chang/ULD.
Forward citations
Cited by 4 Pith papers
-
Understanding Machine Unlearning Through the Lens of Mode Connectivity
Unlearned models usually connect to their originals by smooth low-loss paths, and the smoothness of that path can predict how hard the unlearning task was.
-
Tool Unlearning for Tool-Augmented LLMs
ToolDelete removes a specified tool's usage from a tool-augmented LLM by aligning forgotten-tool queries to a tool-free model's responses, fine-tuning on retained tools, and applying task arithmetic to preserve genera...
-
SoK: Machine Unlearning for Large Language Models
A new taxonomy for LLM unlearning distinguishes removal-intended from suppression-intended methods, and argues that gradient ascent methods functionally behave like suppression.
-
LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats
Most gradient-based LLM unlearning methods achieve behavioral suppression, not true forgetting, and current benchmarks cannot certify that knowledge has been removed.
Discussion (0). Continue with ORCID to comment.