Pith. sign in

REVIEW 6 cited by

Offset Unlearning 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

arxiv 2404.11045 v2 pith:IY4FTLI5 submitted 2024-04-17 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords unlearningllmsblack-boxdatadeltamodelsoffsetalgorithms
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Despite the strong capabilities of Large Language Models (LLMs) to acquire knowledge from their training corpora, the memorization of sensitive information in the corpora such as copyrighted, biased, and private content has led to ethical and legal concerns. In response to these challenges, unlearning has emerged as a potential remedy for LLMs affected by problematic training data. However, previous unlearning techniques are either not applicable to black-box LLMs due to required access to model internal weights, or violate data protection principles by retaining sensitive data for inference-time correction. We propose {\delta}-Unlearning, an offset unlearning framework for black-box LLMs. Instead of tuning the black-box LLM itself, {\delta}-Unlearning learns the logit offset needed for unlearning by contrasting the logits from a pair of smaller models. Experiments demonstrate that {\delta}- Unlearning can effectively unlearn target data while maintaining similar or even stronger performance on general out-of-forget-scope tasks. {\delta}-Unlearning also effectively incorporates different unlearning algorithms, making our approach a versatile solution to adapting various existing unlearning algorithms to black-box LLMs.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. GROM: Gradient-Free Rapid One-Shot Machine Unlearning

    cs.LG 2026-08 conditional novelty 5.0 of 10

    A single closed-form ridge update to selected MLP layers removes targeted knowledge from LLMs in seconds, with state-of-the-art forgetting-utility trade-offs and quantization robustness.

  2. Automating Evaluation of Diffusion Model Unlearning with (Vision-) Language Model World Knowledge

    cs.LG 2025-07 conditional novelty 5.0 of 10

    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...

  3. SoK: Machine Unlearning for Large Language Models

    cs.LG 2025-06 conditional novelty 5.0 of 10

    A new taxonomy for LLM unlearning distinguishes removal-intended from suppression-intended methods, and argues that gradient ascent methods functionally behave like suppression.

  4. Editing as Unlearning: Are Knowledge Editing Methods Strong Baselines for Large Language Model Unlearning?

    cs.LG 2025-05 conditional novelty 5.0 of 10

    WISE and AlphaEdit, two knowledge editing methods, are competitive unlearning baselines when unlearning is framed as editing a model's answer into a refusal.

  5. A Survey on Training-free Alignment of Large Language Models

    cs.CL 2025-08 conditional novelty 4.0 of 10

    A survey that catalogs and categorizes training-free LLM alignment methods into pre-decoding, in-decoding, and post-decoding, with a limited experimental comparison on one model.

  6. A Survey on Generative Model Unlearning: Fundamentals, Taxonomy, Evaluation, and Future Direction

    cs.LG 2025-07 conditional novelty 4.0 of 10

    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.

Pith tools