- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This work, a mechanistic study, investigates how vision-language models (VLMs) structure image representations during few-shot classification. Specifically, the authors uncover a Shared Discriminative Geometry (SDG)—a low-dimensional subspace of hidden-state directions that consistently underpins classification across distinct vision tasks. Causal intervention experiments confirm that these directions directly steer model outputs.
Critical strengths
- The paper discovered a useful observation about information hidden by the default similarity measure. Raw dot-product classification on the forerunner states performs poorly, while a learned compact metric substantially improves classification.
- The evidence from the main three-shot settings supports a functional contribution of the identified directions.
- The authors examine randomized support labels, different shot counts, four-way/four-shot training, and probes trained on individual domains.
Critical weaknesses
- The experimental design fails to validate the proposed dimensionality-reduction mechanism. Candidate heads are selected solely by how well their outputs align with the learned SDG, whereas the theoretical algorithm explicitly requires computing the similarity error (X^TX – Z^TZ). Furthermore, ablating these heads degrades classification accuracy even when the probe retains all 128 dimensions. This indicates that the ablation indiscriminately damages general discriminative features, suggesting that the model actually relies on a higher-dimensional representation rather than the proposed low-rank subspace.
- The paper needs to re-consider the novelty of the work and make comparison against the previous transformer–PCA research. For example, in the paper Learning Spectral Methods by Transformers already constructs transformers whose forward passes approximate PCA through power iterations, while this paper builds a linear-attention development. So, it is rational to add the comparison with prior studies.
- The three main intervention settings do not support the claim that the forerunner tokens are necessary representations. In the appendix, the paper showed that removing top 15 SDG, removing top 15 directions from forerunner and removing all 128 directions will reduce the prediction accuracy. This shows that the directions matter somewhere in the distributed computation but provides weaker evidence that the specific forerunner state is necessary.
Questions for authors
Appendix B.1 states that support and query images are distinct within an episode. I did not find a clear account of held-out images, held-out classes, or the separation between projection-training and evaluation episodes. Could the authors explain more about how to avoid the label leakage?
3 comments
I thank the authors for the detailed rebuttal. Most of my previous concerns are addressed. Therefore, I am happy to raise my score to weak accept.
Thank you for your thoughtful review and for taking the time to reconsider your assessment. Have a great day!
Response to Reviewer NqE4
Dear Reviewer NqE4,
We sincerely appreciate your detailed comments on our work. Your thorough review and helpful recommendations will greatly enhance the manuscript.
[Weakness 1a]: Head selection via XTX−ZTZ
It is true that we select candidate heads based on the OV circuit, whereas using the QK circuit similarity error should be a valid convincing selection criterion. So why the OV circuit?
First, we do not have an exact estimation of the X nor the Z subspace used by the model making the estimation of XTX−ZTZ finicky, especially because it is a difference. The OV matrix in Eq (9) has a simpler theoretical formulation that is easier to identify.
Second, by selecting heads by their OV score and ablating only their cross-image attention, we validate 2 theoretical predictions at the same time. Selecting heads based on XTX−ZTZ and ablating the attention used for selection would focus both steps on the QK side.
We think that using XTX−ZTZ would make the paper’s argument hard to follow and the experiment less reliable. As stated in the paper, our contribution is not identifying exactly the theoretical circuit, but showing the observed dimensionality reduction is possible and that the main mechanism driving it is sample-to-sample attention.
[Weakness 1b]: Ablation degrades all 128 dimensions.
We appreciate your excellent intuition on that question. This needed an additional experiment for clarification.
As you note, the paper ablation reduces accuracy both with the top 10 dimensions and with all 128 dimensions. The 128D drop reflects another phenomenon we already observe in the model without ablation. The accuracy of the remaining SDG dimensions (dimensions 11 to 128) degrades across layers from 90.9% at the input layer to 53.5% at ℓ∗−1. This explains why, in the ablation, the remaining 118 dimensions do little to compensate for the loss of accuracy in the top 10 dimensions. (see Appendix F.2)
[Weakness 2]: Transformer PCA Literature.
We understand your concern and the novelty of our theoretical circuit deserves clarification, specifically regarding the paper "Learning Spectral Methods by Transformers" on arXiv. The authors construct a more sophisticated transformer circuit involving 3 independent steps (Symmetrization, Power Iterations, Removal of Principal Eigenvectors) using MLPs and Attention. Their transformer is capable of constructing principal directions of input data. Our theoretical circuit is much simpler. It differs by only projecting in-context data onto its principal components using only one attention layer for the update. We added a discussion of the relevant PCA literature to the Related Work section of the revised paper.
[Weakness 3]: Forerunner SDG Necessity.
If we reformulate your concern: In Table 10, ablating the SDG dimensions across all tokens costs 11.4 accuracy points, whereas doing the same only for the forerunner token costs 0.5 points. Our interpretation in the paper is that other tokens may carry the SDG information and restore it at the forerunner between layer ℓ∗ and the last layer. However, we agree that in the current paper there is no evidence to support that interpretation.
That is why we designed a simple experiment to show the necessity of the forerunner SDG for the in-context classification task. To that end, we ablate Text SDG only for the forerunner token but from layer ℓ∗ to the last, to prevent any copying of SDG information onto the hidden states. This has a catastrophic effect on model accuracy (-27.9% in 3-shot vs +1.8% for the control random subspace ablation). Details in Appendix E.1.
[Question 1]: Label leakage.
This is a fair question. We made sure that a query image is never in the support set and that we sample train and evaluation episodes with different seeds. However, in the main paper setup, the probe training and probe evaluation image pool are the same. Our probe plays the role of an oracle in the image pool (152,929 images from 10 datasets). This design choice was made to disentangle probe transferability and is important to support some of the paper’s conclusions. When showing that low-dimensional SDG accuracy at the input layer is lower than at layer ℓ∗, we show that our oracle probe found a projection at ℓ∗ that separates classes better than the one it found at the input layer. If we use different images or classes at evaluation, observing that accuracy gap could still leave open whether a different input-layer projection could better separate classes.
Thank you for highlighting this point. We agree that SDG probe transferability is a key claim of our paper, we report results on transfer to unseen classes and domains in our response to Reviewer TEPr Question 1 or Appendix C. The Text SDG transfers well to unseen classes, reaching 90.6% NCC accuracy, just 1.3 percentage points below an oracle probe trained on those classes.