- Rating
- 4(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The authors propose a method to make teacher and student models share the same computational behaviour under interventions and perturbations of inputs and representations. Perturbations of the teacher models representations are "transported" to the student model using learned layer wise abstraction maps. They alternate between learning these maps with fixed student and teacher representations, and learning the student with a fixed map. They compare this with other KD methods on a variety of LLMs on SQuaD, GLUE and yelp review classification.
Critical strengths
- The paper's framing of model distillation as aligning student and teacher responses to interventions on matched representations is interesting and I think may lead to interesting further work.
I would very much like to see the implications of this work on mechanistic interpretability worked through more thoroughly.
- I found this paper very easy to follow, it's experiments section was especially clear and reasoning and assumptions underlying choice of evaluation metric were laid out and reasoned through.
Critical weaknesses
- The most interesting and consequential ideas in this paper are left to further work.
The framing of this paper, at least in the abstract, leans heavily on the potential use of this for mechanistic interpretability, but this actually only makes up a few lines at the start and end.
- Figure 2 shows improved matching on input states doesn't necessarily result in better output mapping, and quite a few of your results have overlapping error bars with the other KD methods. Is there a good reason why someone who doesn't care about the computational/causal fidelity of their student model to the teacher should change their mind and start caring about it, if their only aim is to replace a larger model with a smaller one? Does your method result in distilled models that generalise better for instance?
Questions for authors
In section 4, how does one select a partition? How does the selection of the partition effect downstream results?
4 comments
We thank you again for your time. Please let us know if we have answered your concerns, or if you need further clarifications from our side.
Thank you for your comprehensive and enlightening response. The updated manuscript has improved it on several fronts:
- The contribution of the work is much clearer
- The layer-wise analysis analysis answers my question of how partition selection is performed and impacts performance
- Several parts of the procedure which were not totally clear (fitting of abstraction maps) have now been clarified.
I think this work will be of interest, especially as to how it may inspire further mechanistic interpretability work. As such I raise my score and recommend acceptance.
Official Comment by Authors
Thank you for your positive assessment of our revisions, and for increasing your score.
We also appreciate your encouraging comments.
Response
We thank the reviewer for the positive assessment of our causal-abstraction framing, the clarity of the presentation, and the experimental evaluation. We also appreciate the constructive suggestions regarding mechanistic interpretability, practical benefits beyond causal fidelity, and partition selection.
We agree that the distinction between our demonstrated contributions and potential applications to mechanistic interpretability should be clearer. We have revised the Introduction (Section 1) to clarify that mechanistic interpretability motivates our approach, while the present work focuses on causal abstraction as a training and evaluation principle for model distillation. Constructing human-interpretable mechanistic explanations remains future work.
The present contributions are:
These clarifications distinguish the contributions established in this paper from their longer-term implications for mechanistic interpretability.
We agree that improved internal consistency does not necessarily translate into better output behavior, as illustrated by Figure 2. However, our results show that intervention-aware distillation can also provide practical benefits beyond internal causal fidelity.
Thus, CAB's potential practical value extends beyond internal causal fidelity: it can improve transfer performance and preserve teacher behavior under distribution shifts. However, these benefits are not universal, and we do not claim that CAB consistently outperforms conventional distillation when clean-task accuracy is the sole objective.
We have clarified the partitioning procedure in Section 4 and Appendix B.
Our layerwise reconstruction analysis shows higher errors at S4–S5 than at S1, suggesting that some parts of the teacher may be harder to approximate (Appendix E, Figure 3). While this does not establish an optimal partitioning strategy, it motivates exploring non-uniform or automatically selected partitions in future work.