- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper formulates sense-level behavioral unlearning, which aims to suppress responses associated with one registered interpretation of a shared name or word while preserving responses related to another. It introduces SensePairs and proposes SenseClamp, an inference-time method that combines interpretation routing with hidden-state clamping toward layer-specific retained-reference values in a frozen model. Experiments across three model families demonstrate the effectiveness of SenseClamp and its ability to identify degradation in retained interpretations.
Critical strengths
- The paper introduces a novel task of sense-level unlearning and constructs a paired dataset.By directly evaluating two interpretations of the same surface form, it addresses the limitations of conventional retention evaluations that focus only on unrelated items.
- The paper proposes SenseClamp, an inference-time method for sense-level unlearning, and provides comprehensive experimental evaluations to assess its effectiveness.
Critical weaknesses
- Although sense-level unlearning is a meaningful problem, similar cases may already exist in conventional unlearning benchmarks. The authors should evaluate SenseClamp on standard benchmarks to further demonstrate its advantages over existing methods.
- The comparison with GUARD-IT does not control intervention sites or strength, making it difficult to isolate the contribution of the clamping mechanism. A fairer comparison with matched intervention settings is recommended.
- The refusal baseline achieves higher target-answer flip rates on Llama and Qwen with comparable retention damage. The authors should clarify the practical benefits of SenseClamp over selective refusal.
- Figure 2 does not clearly illustrate the method's workflow, particularly the meanings of different arrows. The figure should better align with the methodological descriptions. Figures 3 and 4 also need improvements in clarity and presentation.
Questions for authors
- Given that the selective refusal baseline achieves better target-answer flip rates with comparable retention damage, what are the practical advantages of SenseClamp over selective refusal?
- Could the authors provide a fairer comparison between clamping and rotation under the same intervention sites and comparable perturbation strengths? Otherwise, it is difficult to determine whether the improvements come from the clamping mechanism itself.
4 comments
W2 & Q2 (Part 2 of 3)
W2
The comparison with GUARD-IT does not control intervention sites or strength, making it difficult to isolate the contribution of the clamping mechanism. A fairer comparison with matched intervention settings is recommended.
Response
We ran the matched comparison you recommend (Table 38 of the revised paper). We applied both clamping and GUARD-IT-style rotation at block 7 of Qwen2.5-7B-Instruct, GUARD-IT’s own edit block (Table 29). For each request, both edits used a direction refitted at that block, identical routing decisions and the same token-position rule. The clamp set the activation coordinate along that direction to the retained reference. The rotation updated the activation along the shared direction and restored its original norm.
Q2
Could the authors provide a fairer comparison between clamping and rotation under the same intervention sites and comparable perturbation strengths? Otherwise, it is difficult to determine whether the improvements come from the clamping mechanism itself.
Response
Yes. We calibrated strength on the development set using mean decoding displacement. At each decoding position, we measured the size of the hidden-state change relative to its pre-edit norm. We averaged these relative changes within each request and then equally across requests. Rotation’s mean was 1.52% above the clamp’s, within the prespecified ±10% tolerance. With the coefficient fixed, rotation’s mean decoding displacement was 3.28% larger on Test.
New same-layer experiment on Qwen2.5-7B-Instruct, SensePairs-Test
| Edit at block 7 | Mean decoding displacement (clamp = 100) | Substantive target suppression rate ↑ |
|---|---|---|
| Retained-reference clamp | 100.00 | 37.28% |
| GUARD-IT-style rotation | 103.28 | 19.91% |
At block 7, clamping achieved 37.28% substantive target suppression on Qwen Test, compared with 19.91% for rotation. The paired 95% interval for the 17.37-percentage-point difference excludes zero. The edit site was identical and mean decoding displacement was approximately matched. This supports a contribution from the clamping rule itself.
W3, Q1 & W4 (Part 3 of 3)
W3
The refusal baseline achieves higher target-answer flip rates on Llama and Qwen with comparable retention damage. The authors should clarify the practical benefits of SenseClamp over selective refusal.
Q1
Given that the selective refusal baseline achieves better target-answer flip rates with comparable retention damage, what are the practical advantages of SenseClamp over selective refusal?
Response
The practical advantage of editing is that it can preserve a correct answer that a fixed refusal would block. The refusal baseline in Table 7 relies on SenseClamp to decide which questions to refuse. On Gemma-Ext, SenseClamp mistakenly selected 31 questions about the meaning to preserve that the base model had answered correctly. The refusal baseline blocked all 31. SenseClamp still answered 16 of them correctly after editing. Averaged equally across requests, editing reduced retained-side damage relative to refusal by 15.3 percentage points on Gemma Test and 18.5 points on Ext. Both paired 95% intervals exclude zero.
On Llama and Qwen, SenseClamp rarely selected questions about the meaning to preserve (Table 18). The refusal baseline inherits that selectivity because it refuses only the questions SenseClamp selects. Retained-side damage was at most 2.2% for both editing and refusal across Test and Ext. The two prompt-based baselines also check for the shared word or name but rely on instructions to tell its meanings apart. With gated prompting on Test and partial-refusal prompting on Ext, retained-side damage ranged from 9.7% to 24.0% on these models (Tables 3 and 4).
As you note, refusal produced more target-answer flips than editing on Llama and Qwen on both Test and Ext, with comparable retained-side damage. Whenever the base model answered a target question correctly, a refusal counts as a flip. Substantive suppression is measured on those same previously correct target questions. To count, the edited answer must be well-formed and non-refusing, with the queried fact absent throughout. The model must also assign the correct reference answer a lower likelihood than before editing. On SensePairs-Test, editing achieved 57.1% substantive suppression on Llama and 68.5% on Qwen (Table 3). We expanded the "Response policy" paragraph of Section 6.2 in the revised paper to state this comparison.
W4. Figure revisions
Figure 2 does not clearly illustrate the method's workflow, particularly the meanings of different arrows. The figure should better align with the methodological descriptions. Figures 3 and 4 also need improvements in clarity and presentation.
Response
Thank you for the specific feedback on the figures. We revised Figures 2, 3 and 4 in the updated PDF.
Figure 2. The dashed arrow passes the fitted parameters to the clamp, the yes and no arrows show whether a query is edited, and the inset arrow shows how one hidden state is updated.
Figure 3. It is now a scatter plot of substantive suppression against preservation of the retained interpretation.
Figure 4. It is now a paired bar chart of the two edits with every value printed.
Follow-up on our response
Dear Reviewer kGRZ,
Just checking in, since the discussion closes on November 18. Both experiments you asked for are in the revised PDF. Table 41 has six methods on 13 RWKU targets, and Table 38 compares clamping and rotation at the same block with roughly the same displacement. We also redrew Figures 2 to 4. We'd really like to hear whether this settles your concerns.
W1 (Part 1 of 3)
Response
Thank you for suggesting an evaluation on a standard unlearning benchmark. We evaluated SenseClamp and five baselines on the 13 RWKU [1] targets that have a same-name referent meeting our criteria. On these requests, SenseClamp gave the best overall trade-off between target suppression and preservation across the three models.
Consider a request to suppress facts about the actor Steve McQueen. RWKU’s original neighbor questions ask about people connected to the actor, such as his co-star James Garner. A model could still answer correctly about Garner even if it could no longer answer questions about the director also named Steve McQueen. Each target and its other referent share a name with identical spelling and capitalization. We required example passages for fitting both referents and at least five separately verifiable facts about the retained referent. We kept RWKU’s original questions and added five questions per name about the other referent, for a total of 65 same-name questions.
We measured how often a previously correct answer became incorrect and averaged that rate across eligible requests. Gated prompting on Qwen illustrates what the original neighbor questions miss. Its damage rate was 0.85% on RWKU’s original neighbor questions and 37.50% on the added same-name questions. On each model, SenseClamp selected none of the 373 original neighbor questions for editing, so all 373 received the same answers as before the intervention.
Human evaluation on 13 RWKU requests (%). For each model, S ↑ is substantive target suppression on original RWKU target questions. Related ↓ and Same-name ↓ are damage rates on original neighbor questions and added same-name questions, respectively. Table 41 in the revised paper gives the eligible question counts. The same-gate refusal control replays SenseClamp’s routing decisions, returning a fixed refusal on selected questions and the stored base answer on the rest. On previously correct target questions, this gives a substantive suppression rate of 0.00%.
On every model, SenseClamp had the highest substantive suppression of the six methods on the original RWKU target questions, and it preserved every previously correct answer to the original neighbor questions. On the added same-name questions, its damage was zero on Gemma and Llama and 6.25% on Qwen.
Reference
[1] Zhuoran Jin et al. 2024. RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024, Datasets and Benchmarks Track.