- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes latent transition alignment (LTA) for replay-free continual learning of language models. It uses frozen encoders to compare cross-layer transitions between a reference model and the model being trained. The loss aligns transition directions and penalizes excessive magnitude growth. An offline dual-anchor construction and latent fixed-point analysis motivate this objective. Experiments report lower reference-NLL drift and better first-domain retention across several task orders, with an additional transfer experiment on Qwen2.5-3B.
Critical strengths
-
LTA offers a clear alternative to matching individual hidden states. It allows common endpoint shifts and some magnitude changes, without adding inference-time components.
-
The structural baselines and component ablations offer useful controls.
Critical weaknesses
- The novelty over existing cross-layer distillation is not that clear.
FDD (Gong et al., 2025) already aligns cross-layer changes using cosine distance in its layer-delta loss (Eq.~7). LTA uses the same form of angular penalty, but applies it in a learned latent space instead of the LM-head log-probability space. The dual-anchor construction, reference-dependent weighting, and one-sided magnitude term distinguish LTA from FDD. However, this work does not clearly establish how much these additions improve upon prior directional alignment.
Transition-MSE matches complete vectors and hence doesn't represent FDD's cosine-based objective. The Direction-only ablation is useful, but it retains LTA's dual-anchor encoder and doesn't isolate the benefit of that construction. Moreover, Table 5 reports nearly identical mean reference drift for Direction-only and full LTA, at 0.0221 and 0.0220, respectively. This provides limited evidence for the added magnitude term. A matched FDD-style baseline and an encoder ablation without the second reconstruction anchor would help show whether LTA offers a substantial methodological advance over existing transition alignment.
- The attractor analysis doesn't show what the online LTA loss preserves.
Theorem~B.4 requires uniform bounds on both map differences and Jacobian differences over a neighborhood. LTA instead constrains sampled transition directions and excessive magnitude growth. This paper doesn't show that minimizing this loss controls either bound. For example, away from the numerical stabilizer, a positive contraction , with , can incur no structural penalty despite changing the transition magnitude. Moreover, the fixed-point diagnostics use a different reconstruction chart from the online method. These results motivate transition alignment, but do not show attractor preservation by LTA. Measurements in the actual Qwen dual-anchor space would make this connection more convincing.
- Baseline calibration doesn't give a fair retention-learning comparison.
LTA undergoes multi-dataset calibration, while Output KL uses a fixed weight of one, and the other structural baselines use gradient-based scale matching. Freezing these choices before formal evaluation is useful, but it doesn't establish comparable tuning budgets or optimal operating points. The learning trade-off also matters. On ReClor, LTA reaches 68.16% accuracy, compared with 70.92% for SFT. So, the abstract's statement that LTA matches SFT is too broad. Retention-accuracy curves under a shared development protocol would provide a stronger comparison than one selected setting per method.
Other minor issues, e.g.:
-
Line 052: "an transition–field" => "a transition–field"
-
Line 053: Missing a space in "reconstruction.Online"
-
Figure 9 caption: The right panel shows a fixed point and perturbation returns. Yet, the displayed right panel instead shows a cosine-similarity distribution.
Questions for authors
-
Can you provide the full task-by-stage accuracy matrices, including later-task acquisition, and explain how the retention conclusions change after accounting for differences in first-task learning?
-
What evidence connects the online loss to attractor preservation in the actual Qwen dual-anchor space? Does the second anchor improve results over start-anchor-only reconstruction?
4 comments
Reply 2: Actual Qwen dual-anchor space, attractor-informed dynamics, and the second-anchor contribution
Question: What evidence connects the online loss to attractor preservation in the actual Qwen dual-anchor space?
Sample-conditioned dual-anchor maps and the attractor-informed motivation.
The dual-anchor construction provides a sample-conditioned dynamical interpretation. For each input and token context, the shared encoder maps both endpoints of a Transformer window into a common latent coordinate system, and the decoder reconstructs both endpoint codes as the same window-input state.
Under exact reconstruction, this induces a context-conditioned latent self-map. The end code is a fixed point of this sample-conditioned map, while the observed start-to-end transition equals the residual-field vector at the start code.
From sample-conditioned fixed points to the population-level transition field.
The surrogate is fitted jointly across many training examples and contexts. It therefore aggregates these sample-conditioned transition–field relationships into a population-level transition field that captures the original model's collective latent processing behavior. Each example and context can induce its own fixed point. The learned population field represents the aggregated dynamics across these sample-conditioned relations and does not require a single global fixed point shared by all examples.
Online LTA preserves this attractor-informed field through directional alignment and one-sided magnitude control. Direction alignment preserves the orientation of observed transitions. The magnitude term penalizes excessive radial expansion while leaving contractions unpenalized. Its speed-dependent weighting assigns greater confidence to low-speed reference transitions, protecting the low-speed region of the transition geometry while retaining flexibility for adaptation.
Evidence in the actual Qwen2.5-3B dual-anchor charts.
We measure transition–field correspondence in the actual Qwen2.5-3B dual-anchor charts. Across three domains and two frozen windows, correctly paired cosine similarities range from 0.2158 to 0.4494, compared with 0.0018–0.0673 for shuffled-context, shuffled-transition, and cross-domain controls. Correct pairing is consistently stronger across all six domain-window combinations.
The adapted QASC population-geometry analysis provides complementary evidence. Full LTA reduces covariance-shape distortion from 0.451650 for Direction-only to 0.347517, a 23.1% reduction. Effective-rank displacement decreases from 3.17927 to 1.08884, a 65.8% reduction. These measurements connect the online objective to preservation of the population-level transition-field geometry.
We retain Theorem B.4 as a conditional persistence result under its stated neighborhood-wise map and Jacobian conditions. The actual-chart measurements establish the empirical transition–field correspondence and population-geometry preservation underlying the attractor-informed formulation.
Question: Does the second anchor improve results over start-anchor-only reconstruction?
Second-anchor ablation: DA, SA, and EA.
We directly isolate the second-anchor contribution through matched representation ablations. Dual-Anchor Reconstruction (DA) reconstructs the window input jointly from both endpoint encodings. Start-Anchor Reconstruction (SA) reconstructs the window input using only the start-endpoint encoding. Endpoint Autoencoding (EA) reconstructs each endpoint from its own encoding. All three learned representations use the same 128-dimensional surrogate architecture, 3,000-step fitting budget, and online directional objective.
| Representation | ReClor accuracy | ReClor ΔNLL | Sequential final mean | First-task forgetting | Cumulative ΔNLL |
|---|---|---|---|---|---|
| DA | 68.13±0.70% | 0.01496±0.00112 | 64.96±0.37% | 24.44±1.08 pp | 0.15822±0.00689 |
| SA | 69.53±0.83% | 0.01631±0.00092 | 63.64±0.37% | 27.44±1.84 pp | 0.17430±0.00603 |
| EA | 67.67±0.31% | 0.02306±0.00112 | 64.61±0.24% | 25.33±1.86 pp | 0.20509±0.00744 |
After selecting on ReClor and freezing it for QASC→Chemistry→ReClor, DA achieves the highest final mean accuracy, the least first-task forgetting, and the lowest cumulative drift. Relative to SA, DA improves final mean accuracy by 1.32 pp and reduces cumulative drift by 9.2%. This directly demonstrates the incremental value of the second reconstruction anchor over simpler representations under the same online directional objective.
Reply 3: FDD, magnitude ablation, and matched-accuracy calibration
Question: How much do these additions improve upon prior directional alignment?
FDD as a direct cross-layer directional-alignment baseline.
We agree that FDD is a strong and closely related method, and we have now included it as a baseline in our comparisons.
We added FDD as a direct baseline for cross-layer directional alignment. FDD uses four uniformly spaced Transformer states, projects them through the model's own LM head into full-vocabulary log-probabilities, and aligns adjacent-state derivatives using cosine distance. FDD-full additionally includes full-vocabulary output KL and intermediate trajectory KL. This comparison directly tests LTA against a closely related prior cross-layer distillation objective.
Five-seed 1.5B FDD comparison.
Across QASC/Chemistry/ReClor, LTA Direction-only achieves lower five-seed mean General-reference than FDD-direction in all three domains: 0.03424/0.02498/0.00711 vs. 0.10402/0.06093/0.05058, reductions of 67.1%/59.0%/85.9%, respectively. Full LTA also achieves lower drift than FDD-full on QASC (0.03194 vs. 0.04135; 22.7% lower) and ReClor (0.00701 vs. 0.01331; 47.3% lower). On Chemistry, FDD-full has lower drift than Full LTA (0.01282 vs. 0.02693). The complete five-seed per-domain results and curves are provided in the supplementary material.
Five-seed Qwen2.5-3B Direction-only ablation: the magnitude term's independent benefit.
We added a complete five-seed Direction-only ablation on Qwen2.5-3B QASC, using the same 300-update evaluation protocol. The results directly isolate the one-sided magnitude term:
| Method | QASC accuracy | Aggregate ↓ |
|---|---|---|
| Full LTA | 77.17±3.21% | 0.01080±0.00235 |
| Direction-only | 78.67±1.07% | 0.01796±0.00620 |
| FDD-full | 79.67±0.47% | 0.02666±0.00423 |
Full LTA reduces aggregate drift by 39.8% relative to Direction-only and 59.5% relative to FDD-full. These results quantify the retention contribution of the complete LTA objective relative to both a matched directional ablation and a strong prior baseline.
We also completed the full five-seed 1.5B sequential Direction-only matrices. Across orders A, B, and D, Full LTA obtains a macro-average first-task forgetting of 10.22 pp, compared with 11.84 pp for Direction-only, and a final mean accuracy of 68.54%, compared with 68.12%. In the QASC-first order, Full LTA improves final QASC accuracy by 4.70 pp and reduces first-task forgetting by 3.67 pp. The complete matrix is provided in supp/rebuttal_supplement/results/1P5B_DIR.md.
Independent magnitude stress test under severe update pressure.
To further isolate the magnitude term, we conducted a separate ReClor learning-rate-pulse stress test. The multiplier is applied only during updates 101–120, after which the base learning rate is restored.
Under the strongest intervention:
| Method | Step-120 accuracy | Recovery (120→300) | Step-300 accuracy | Final aggregate |
|---|---|---|---|---|
| Direction-only | 27.73±2.10% | 39.67±0.90 pp | 67.40±1.20% | 0.07448±0.00472 |
| Full LTA | 26.60±1.91% | 42.60±1.11 pp | 69.20±0.80% | 0.06103±0.00349 |
The magnitude term improves post-shock recovery by approximately 2.93 points, final accuracy by 1.80 points, and final aggregate reference retention by reducing drift by 18.1%. From to , the additional drift increase is also 13.9% smaller with Full LTA. These results establish the practical role of one-sided magnitude control in recovery and final retention under strong update overshoot.
Question: Do the main retention gains hold at matched target accuracy, or under comparable coefficient-search budgets?
Matched-accuracy coefficient calibration on ReClor.
At matched target accuracy, do the main retention gains remain? Do they persist when LTA, Output-KL, and Transition-MSE receive comparable coefficient-search budgets?
We added a shared development-set coefficient sweep on 1.5B ReClor single-domain adaptation, using development seed 2026, a common relative grid , and a pre-specified SFT−1 pp accuracy threshold. Among candidates meeting the threshold, we selected the operating point with the lowest aggregate reference .
Under this threshold, Full LTA has a feasible point at 68.9655% accuracy / 0.0145558 drift. The best Transition-MSE point is 68.3190% / 0.0264799, while Output-KL has no candidate meeting the threshold. These results directly characterize the learning–retention trade-off under a shared development-set search protocol.
Question: Other minor issues: wording, spacing, and the Figure 9 caption.
Manuscript revisions and reproducibility.
We have corrected the manuscript's wording from “an transition–field identity” to “a transition–field identity,” inserted the missing space in “reconstruction. Online,” and corrected the Figure 9 caption to identify the right panel as the transition–field cosine distribution.
We have also revised the manuscript: Fig. 6 now includes the FDD baseline, Fig. 7 includes the Direction-only ablation, and Fig. 8 presents both the FDD and Direction-only ablation curves. We have additionally added the FDD citation at line 373.
The supplementary package at supp/rebuttal_supplement/ includes the complete per-seed result matrices, fixed experimental protocols and configurations, reproduction code, detailed experiment documentation, and machine-readable tables, facilitating independent verification and reproduction.
Response to Reviewer qM5f
We sincerely thank you for your careful reading and constructive feedback. We have carefully considered your concerns about the novelty of the transition objective, the attractor interpretation, and baseline calibration. We have added direct comparisons, component ablations, and mechanism measurements to address these points.
Reply 1: Complete sequential matrices and retention after later-task learning
Question: Can you provide the full task-by-stage accuracy matrices, including later-task acquisition, and explain how the retention conclusions change after accounting for differences in first-task learning?
Complete task-by-stage accuracy matrices.
We have now summarized and provided the complete task-by-stage matrices for all three task orders, five paired seeds, and five formal methods. The supplementary matrices contain 900 unique task-by-stage cells and 75 complete trajectories, with all three tasks evaluated after every 300-update stage. The complete matrices are available in
supp/rebuttal_supplement/results/1P5B_CL.md.First-task retention and later-task acquisition.
The paired comparison with Output-KL shows that Full LTA reduces first-task forgetting in all three orders:
The paired confidence intervals for first-task forgetting exclude zero in all three orders. The complete matrices also report second-task acquisition and retention, third-task acquisition, and final three-task mean accuracy, allowing the learning–retention trade-off to be evaluated across the entire sequence.
The QASC-first order gives the strongest terminal gain: final QASC accuracy improves from 43.83% to 51.13% (+7.30 pp, 95% CI [+2.46, +12.14]), and final three-task mean accuracy improves from 62.77% to 64.23% (+1.46 pp, 95% CI [+0.23, +2.68]). In ReClor→QASC→Chemistry, final ReClor accuracy improves by 2.64 pp and final QASC accuracy improves by 2.53 pp. The final three-task mean increases by 1.04 pp.
We report acquisition and retention together. In the QASC-first order, the initial QASC difference is −0.90 pp and the final QASC difference is +7.30 pp. In ReClor→QASC→Chemistry, the initial and final ReClor differences are −2.72 pp and +2.64 pp. The complete matrices also include second-task forgetting F2 and all final task accuracies.