- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
The paper introduces a training-free method to unlearn certain code data that was seen during training, through inference-time steering of hidden states. Given a forget dataset and a retain dataset, a three-stage solution is proposed. First, the subset of important hidden states that need steering are determined by a projection taking into account the variance of both forget and retain groups, followed by comparing against the mean of the retain group. Next, the direction along which to move the hidden states is determined by the forget group. Finally, the intervention strength is calibrated to minimize degradation on generation utility. Experiments are performed on two corpora, each of 300 forget examples and 8280 retain examples. Results show that the proposed method effectively reduces reproduction of the forget examples, while largely maintaining generation accuracy.
Critical strengths
- The proposed method intuitively makes sense and is effective under the paper's experiment setup.
Critical weaknesses
- The practical usefulness of the proposed method is unclear. The motivation mentioned in the introduction is to unlearn samples that have copyright or security concerns. Per my understanding, those mainly target pre-training data. The problem is that the method does not scale to pre-training-level data, in which case the retain set would contain trillions of tokens. It only works on small datasets, but retraining in such cases is cheap enough and more robust than inference-time patching.
Questions for authors
None
3 comments
Response to Reviewer tHa4 Part2
(continued from Part 1)
Does the method scale with the retain set? UNBIND does not train on the retain set. It only needs (i) first- and second-moment statistics of retain hidden states for the detector and (ii) a small calibration set for the budget. Both saturate quickly. Varying the retain fit data from 60 rows to the full pool, FU-H saturates at about 1,920 rows (Qwen-CSN 98.98 vs. 98.99 with the full pool; StarCoderBase 82.70 vs. 82.37). The statistics can be accumulated in a streaming fashion, so the cost is linear in the number of retain tokens processed. In our experiments, the required amount saturated at about 1,920 rows instead of growing with the size of the pool (Section 5.7, Table 5, Appendix G.2).
Is retraining cheaper and more robust?
- Pretraining memorization. Retraining a base model is out of reach, while UNBIND needs only a few GPU-hours of calibration.
- Fine-tuning memorization. A single UNBIND calibration costs less than one retraining (1.44 vs. 1.80 GPU-h on Qwen-CSN). Later requests are handled incrementally in about 13 min each, while retraining must be repeated for every request.
- Robustness. UNBIND's FU-H is higher than the retrained model's in all four settings (96.27–98.79 vs. 62.03–86.63). Under eight extraction attacks, merged N50 is 0–10 for UNBIND, vs. 95 for M_retrain on Qwen-Stack (Appendices G.4, G.9, G.11).
Thank you for the response. To clarify my concern with scalability, the proposed method needs to work with matrices such as or , with . Those matrices grow linearly or quadratically with the size of forget or retain sets. At pre-training scale, both sets can grow up to million or billion level, making those matrices unmanageable.
The Part 2 rebuttal seems suggesting that we only need a small subsample of . It's not straightforward to me why a few thousand samples can effectively represent the full pre-training distribution which should be retained. Furthermore, this does not address the case where we want to unlearn millions of samples.
Response to Reviewer tHa4 Part1
Pretraining data and trillion-token retain sets. We directly tested unlearning of pretraining memorization in two base models, with no fine-tuning.
Qwen2.5-Coder-7B-Instruct (pretraining memorization, 300 targets):
StarCoderBase-7B (pretraining memorization, 300 targets):
(*MemFree blocks 10-gram matches by construction; after identifier normalization, 38 targets still leak ≥ 32 tokens.)
What these results show: