- Rating
- 2
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 3(+1)
- Soundness
- 2(+1)
Read review
Paper summary
This paper investigates whether refusal steering in MoE models can be decomposed into expert-specific contributions. The authors further find that the most steerable layer does not necessarily contain the most steerable individual expert.
Critical strengths
- Expert-level analysis of refusal steering.
- Interesting single- and all-expert steering settings.
Critical weaknesses
- Limitations in experimental design.
- Lack of in-depth mechanistic analysis.
Questions for authors
The authors explore two approaches to expert-level refusal steering in MoE models: single-expert and all-expert steering. By comparing fixed and flexible intervention locations, they find that the most steerable layer does not necessarily contain the most steerable expert. While the paper provides interesting insights into the role of individual experts in refusal steering, I have the following concerns:
-
Impact of post-attention residual activations on refusal steering. It is valuable to investigate how individual experts contribute to refusal behavior in MoE models. However, I think the current experimental design does not sufficiently support the authors' conclusions. In ActAdd, the steering vector is extracted from the full layer output, which includes the post-attention residual stream and the aggregated expert outputs. In contrast, expert-level steering vectors are extracted only from individual expert outputs, without directly incorporating the post-attention residual stream. Therefore, the observed differences in steering effectiveness may also be influenced by refusal-related information in the post-attention residual stream. I suggest that the authors further investigate its contribution to refusal steering before drawing conclusions about the role of individual experts.
-
The role of KL divergence in experimental comparisons. If I understand correctly, KL divergence is an important factor in ensuring a fair comparison across different steering settings. The authors should ensure that different steering methods result in comparable KL divergence values, so that differences in ASR can be attributed to steering effectiveness rather than varying degrees of disruption to the model's original behavior. Although KL divergence is used during candidate selection, it is unclear whether the final selected interventions across different settings achieve similar KL divergence values. I would appreciate more details and analysis on this aspect.
-
Readability and presentation. The paper's structure and presentation could be improved for better readability. For example, the introductory paragraph of Section 3 (Methods) contains extensive experimental details, which could be moved to the Experiments section. In addition, some mathematical notations could be more standardized. For instance, instead of using kl and rs to denote the KL-divergence and refusal scores, the authors could consider using a more consistent notation. Finally, some experimental results would benefit from clearer explanations. For example, the reported 54%–78% ASR recovery around line 302 is not immediately clear. Only after carefully examining Table 1 did I realize that these values refer to the averages of the corresponding columns. Explicitly stating this would improve readability.
3 comments
Hello, We wanted to send a gentle reminder as the discussion deadline is approaching. We hope our response and the additional experiments addressed your concerns, and we would be grateful if you could reconsider your assessment in light of our revised response. We would also greatly appreciate any further feedback you may have before the deadline. Thank you again for your time and consideration.
Thanks for your clarification. My second and third concerns have been resolved, but the first remains unresolved. I'd like to increase my Presentation and Soundness scores while keeping my Overall Rating unchanged.
rB1H Rebuttal (1/1)
Thank you very much for your time and consideration in reviewing our paper. We have uploaded a revised manuscript that reflects your and other reviewers' feedback and have summarized the changes therein in a general comment to our submission. We will refer to the changes outlined there in our response so as not to repeat content in multiple places.
To briefly address your questions, in order:
While our work demonstrates that the MoE sublayer holds only partial refusal signal, we leave for future work a decomposition of the remaining signal coming from both the attention output and the residual stream from previous layers. We have edited the language in our contributions section to better reflect the sources in our decomposition:
We have added a visualization of "non-response" (degenerate) generations and ASR vs KL-divergence (Figure A1) and a table of KL-divergence values for the selected intervention locations (Table A6) as Appendix E.2. We briefly explain that, while KL-divergence is positively correlated with response degeneration, we account for this by including degenerate responses as steering failures and by balancing KL-divergence with ASR in our selection criteria. Based on this design and the evidence in Table A6, we are confident that differences in ASR reflect steering effectiveness rather than model disruption.
Thank you for these notes on clarity. We have made the following changes in our manuscript based on your and other reviewers' feedback:
Thank you again for your time and attention in helping us to improve our paper. We hope that these additions address your concerns about experimental design and clarify the scope of our mechanistic claims, and welcome further discussion as needed.