- Rating
- 3
- Confidence
- 1
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper uses nGPT’s native parameterization, with unit-norm weight vectors on hyperspheres and explicit Euclidean scale parameters, to break forgetting during domain-adaptive continued pretraining into a rotation channel and a scale channel. Using a Fisher/KL local model around the pretrained point θA, the authors argue for two claims:
- Rotational damage at matched angle depends on alignment with a low-rank task-A-sensitive tangent subspace.
- Scale damage, carried mainly by the output logit scales s_z, depends on the variance under p_A of the per-token logit reweighting (E_S), not on the norm of the displacement.
Critical strengths
- Overall, using nGPT’s native geometry as a coordinate system for forgetting is a natural and underexplored idea.
- The matched-angle rotation probes and the 280 synthetic s_z probes over eleven orders of magnitude in E_S are proper interventions. The sensitive subspaces and E_S are fixed from θA beforehand, so the tests are not circular.
- The cancellation finding is the most interesting result.
Critical weaknesses
- The author state “This localizes the cancellation but does not explain why it is nearly exact.” I_end ≈ −K_s holds to within a few percent on code and medicine and is left as an observation. Several hypotheses seem testable with the existing infrastructure: (1) Does the optimizer drive output scales and output rows toward a logit-preserving equivalence class, given that z_v = s_v⟨h, w_v⟩ has approximate symmetry in which magnitude can be traded between s_v and the effective projection after h shifts? (2) Is the cancellation specific to nGPT, where s_z exists explicitly, or would an unnormalized model show the same effect inside the row norms of W_out?
- there's only one model size (0.5B) in in the paper. Such an undertrained model may sit in an unusual curvature regime.
Questions for authors
- Can you explain why I_end ≈ −K_s so precisely on code and medicine? Is there an approximate reparameterization symmetry among s_z, the output rows, and the hidden state that the optimizer exploits?
- How does the rotation penalty compare with a full K-FAC EWC penalty in ambient (non-tangent) coordinates, using the same statistics? This would separate the contribution of nGPT geometry from that of non-diagonal curvature.
- Does the normalization miscalibration (Table 3) persist if you use the true Fisher (labels sampled from p_A) instead of the empirical Fisher for the K-FAC factors?
4 comments
Follow-up to Reviewer aQrc: Responses to Your Questions
Thank you again for your insightful review and suggestions. We have conducted additional experiments addressing all three of your questions, including analyses of the cancellation phenomenon, full ambient K-FAC EWC comparisons, and predictive-Fisher tests. As the discussion period nears its end, we would greatly appreciate any feedback on our responses.
I thank the author for thorough rebuttal. The new logit-level measurement and the K-FAC EWC comparison are informative. However, the core question of why the cancellation is nearly exact remain open, and the single-model-size concern is acknowledged but not addressed. The rebuttal also weakens two stated contributions: the EWC gap comes from row weighting rather than nGPT geometry, and held-out subspace coverage is far below the reported in-sample figures. I therefore maintain my score.
Thank You for Your Feedback and Clarifying Our Research Focus
Thank you for your thoughtful follow-up and for carefully considering our additional analyses. We agree that understanding why the near-exact cancellation emerges and validating our findings at larger model scales remain important future directions. We also appreciate your comments on the EWC comparison and Fisher subspace coverage, which have helped us refine our claims and clarify their limitations. We hope the revised manuscript better conveys our central aim: to develop a clearer mechanistic understanding of forgetting through the interplay of rotation and scale, rather than to establish the superiority of a particular regularization method. We believe the additional analyses help clarify both what this perspective reveals and what remains to be understood. Thank you again for your constructive feedback, which has been valuable in sharpening the focus of our work.
Response to Reviewer aQrc
We thank the reviewer for the careful review and the precise, testable suggestions (we ran all three), and for recognizing the probes as non-circular interventions and the cancellation as the most interesting result.
Summary. Q1 / W1: a token-selective insensitivity, formed during training; why it forms remains open. Q2: the EWC gap is lm_head row weighting; no advantage from the geometry. Q3: Table 3 was our unit error.
Q1 / W1. Why I_end ≈ −K_s, and is it specific to nGPT? It is realized as a token-selective insensitivity to the learned s_z change, and appears, much weaker, in unnormalized GPT; why optimization produces it remains open. We tested hypothesis (1) at the logit level.
Measurement. Since z_v = s_v⟨h, w_v⟩ (unit h, w_v), all four combinations of {θ_A, endpoint} × {s_z, all other parameters} follow exactly from two forward passes. Let p_R be the model with all non-s_z parameters at the endpoint and s_z at θ_A, and p_B the endpoint. The endpoint's s_z change alone costs K_sz = 1.57 (code) / 1.71 (medicine) nats at θ_A (the all-scale K_s is 1.88). Two distinct measurements: (a) θ_A-referenced, the s_z-only interaction is I_z/K_sz = −1.00 / −0.96; (b) directly, KL(p_R‖p_B), how much the same s_z change still moves the adapted model, is only 3% / 2% of K_sz. (b) is not algebraically identical to I_z; both show this insensitivity.
It is not a general insensitivity. For any scale change d we use M(d) = KL(p_R‖p_R+d) / KL(p_A‖p_A+d). The same s_z log-ratios permuted across tokens give 77–89%, and another domain's s_z change 40–49%. Transplanted onto the rotation-penalized code model, the unregularized run's own s_z change keeps 89% of its effect, so it is largely absent under the rotation penalty.
Not simple reciprocal rescaling. A trade s_B,v⟨h_B, w_B,v⟩ ≈ s_A,v⟨h_A, w_A,v⟩ predicts slope −1 between per-token log scale ratio and log change in mean output cosine; we find −6.0 (code) and −5.6 (medicine). This rules out that simple form, not every approximate symmetry.
It develops during training (reply to k9Kf, W4); these controls concern the endpoints. For (2): the GPT interaction is negative at all six endpoints, but its norm channel is small (reply to k9Kf, W4), so nGPT exposes the size and precision of the cancellation, not its existence. Revised: §5.3, App. C.7.
Q2. Full ambient K-FAC EWC with the same statistics. It forgets more at matched adaptation, a gap largely explained by its lm_head row weighting in our code experiment; with equalized rows the two reach the same trade-off. We implemented λ Σ tr(R ΔW C ΔWᵀ) with both K-FAC factors from the task-A statistics, per-matrix normalization and unpenalized scales (code):
Last row: our raw rotation-only sweep, interpolated; EWC forgets 0.21–0.39 nats more.
The gap is localized to lm_head row weighting. Ambient K-FAC weights lm_head rows by E[δ_v²] and wte rows by input-token frequency, so rare-token rows are nearly free; our penalty weights rows equally. Under EWC lm_head rotates 41–51° at every λ (rotation-only: 2–6°). We changed only this, replacing the diagonal row factor by its mean:
lm_head now rotates 3° and the gap vanishes (within 0.013 nats); with lm_head alone equalized, wte still rotates 12°, so in this code run (one seed) lm_head row weighting explains nearly all of the gap. With equal row weights, the two penalties reach the same trade-off but split the damage differently (EWC: K_w 0.14 vs. 0.24, K_s 0.26 vs. 0.18). We claim no performance advantage from the geometry; it makes this split observable. Revised: §5.2, App. C.5, App. A.
Q3. Does the normalization miscalibration persist with the true Fisher? No, and the miscalibration itself was an error on our side.
W2. One model size. Agreed: all analyses are at 0.5B; the limitations say so, and we make no scaling claim.