- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper formalizes expert sharing across layers or computational roles in multi-step reasoning. It defines role-level event losses, derives exact expected risks for separate fitting, full pooling, partial pooling, and arbitrary partitions, and shows that pooling is beneficial when the variance saved by removing an expert exceeds the functional heterogeneity (sharing bias) between roles. It then composes the fitted role estimates through a fixed linear map and derives an exact terminal-risk expression that depends on the propagation geometry and error covariance. This yields a strict local-to-terminal reversal: a sharing rule can lower average local error while increasing final-output error. For general routed programs, the paper gives conditional error certificates that include implementation mismatch, state propagation, and route changes. Finally, it argues that observational route labels do not identify expert-level operations and proposes intervention-based audits.
Validation consists of controlled Monte Carlo estimation experiments, a three-event linear composition experiment, and small Transformer experiments on modular arithmetic. The controlled experiments match the analytic risks and reproduce the reversal. The Transformers show lower teacher-forced one-step error for tied experts in a low-data sweep, but no statistically resolved free-running final-output improvement; intervention-supervised models achieve high compound-action fidelity, while single-layer attribution and unseen-transition generalization remain limited.
Critical strengths
-
A precise local-to-final distinction. The paper does more than state that composition can matter: it gives an exact risk formula and a concrete reversal where pooling improves local risk but increases terminal risk. This is consequential because many evaluations of expert sharing report only teacher-forced or per-call metrics.
-
Careful treatment of attribution. The proposition that correct route labels and natural predictions do not imply causal reuse is important, and the intervention protocol makes the missing evidence explicit. This prevents a common over-interpretation of routing visualizations.
Critical weaknesses
-
The empirical task is too limited to establish broad practical impact. The learned-model evidence is confined to a small modular-arithmetic task. At one end, the short-horizon models are nearly perfect; at the other, the longer-horizon models are close to failure. This leaves limited evidence about expert sharing in a realistic, non-saturated multi-step reasoning regime.
-
The main theory-to-practice link remains conditional. The strongest exact claims concern controlled linear propagation, while the general routed-program result is an error certificate under additional assumptions. The paper therefore establishes that local-to-final reversals are possible, but does not yet show how reliably the proposed criteria predict final performance in a trained Transformer.
Questions for authors
-
Can the authors provide an end-to-end comparison in a non-saturated multi-step setting where both separate and shared models achieve meaningful but imperfect terminal accuracy?
-
Which assumptions of the general certificate can be checked in the Transformer experiments, and does the certificate make a quantitatively useful prediction of the observed final-output comparison?
2 comments
Reply to Reviewer F8RX (2/2): W2, Q2 and summary
W2. The theory-to-practice link remains conditional: the paper shows that reversals are possible, not how reliably the criteria predict final performance in a trained Transformer.
Answer. Agreed, and the answer differs by level. On trained Transformers, held-out one-step selection found the final-error minimizer in 10 of 10 seeds between chance and saturation, and every one-step gain resolved at both endpoints kept its sign. The rules that plug in the paper's own quantities add little: the plug-in rule of Theorem 1 is correct in 76 of 107 cells against 102 for always fitting separately, and selection with the terminal geometry gains 0.29 pp on average, with opposite signs across layers. What the theory adds to plain validation is when a one-step comparison can be trusted (row 1), a constructed case where it fails (row 3) and the term to check first, routing (row 4).
| Level of the theory | Prediction | Test on trained Transformers | Outcome |
|---|---|---|---|
| Uniform propagation (analogue of §N.4, not an application of it; measured one-step error, not B and C) | A one-step gain resolved at both endpoints keeps its sign, given uniform propagation and composing step errors, both measured (§R.3) | Five sharing patterns; sharing-strength ladder; horizon 12 | Same sign in 145 of 145, 24 of 24 and 15 of 15 such pairs (of 400, 250 and 60 contrasts) |
| Validation selection (Proposition 11; router supervised) | Held-out one-step selection is near-optimal for the local loss (guaranteed); that it also finds the best final strength is an empirical finding | Ladder: 5 strengths, 5 budgets, 5 seeds | Minimizer in 10 of 10 seeds at 96 and 128 traces; 20 of 25 cells overall |
| Exact frontier, uneven propagation (Theorem 46, §N.4) | For a target constructed from the measured geometry, pooling lowers local risk and raises terminal risk | Linear maps with synthetic noise at the four depths of six trained networks (terminal = final hidden state) | Reversal in 6 of 6 with routes fixed. Natural rerouting: 3 of 6 (terminal risk falls in the other three); optimum within one grid step in 7 of 18 settings. No two trained models show a reversal |
| Certificate of Theorem 4, per-call terms (Eqs. 19–20; finite-class terms of Eq. 22 not evaluated) | With routes on plan it tracks the final error; otherwise the routing term can decide the comparison | Measure the per-call terms; supervise the router only | Ratio 0.89 to 1.22 at final error 2–20% (ten runs); a deficit of 23.6 and 44.3 pp becomes an advantage of 21.1 and 4.4 pp |
Q2. Which assumptions of the general certificate can be checked in the Transformer experiments, and does it make a quantitatively useful prediction of the final-output comparison?
Answer. As a measured diagnostic, yes when routes follow the plan and no under learned routing; it is not a prediction made before training. Its per-call terms are measured at the model's own states at 160 checkpoints (§R.4).
Assumptions.
- Not checkable here. Theorem 4 assumes fixed finite classes, probe laws fixed independently of the fitting data, matched ERMs and Assumption 3. Jointly trained Transformers are not fitted this way (§B.2), so the finite-class terms of Eq. (22) are not evaluated; §R.4 measures the recursion below Eq. (20).
- The per-step inequality p_j ≤ a_j + r_j. No violation in any record.
- Routing discrepancy r_j of Eq. (20), measured by forcing another expert at the same pre-call input. The nearest substitute does less harm than the farthest in 6 of 6 full-budget checkpoints (Table 12) and in 19 of 24 low-budget ones (Table 13; 2 of 6 at 96 traces; the five exceptions have natural error of at least 85%).
What was measured.
- Routes on plan. The certificate is 3.17% against a final error of 3.17% (shared, router supervised) and 8.26% against 7.72% (dense block) at 128 traces. The certificate is then a sum of per-step errors, so this closeness shows that the unrolling loses little. Over the ten runs with final error between 2% and 20% the ratio is 0.89 to 1.22 (1.3 and 1.6 in the 96-trace means, above 1 at chance); the four values below 1 are within 1.7 standard errors. It orders these two models as the final error does in 16 of 16 resolved pairs.
- Learned routing. The certificate exceeds 1. The implementation and routing discrepancies are 0.34 and 0.21 per call at 96 traces, and 0.21 and 0.19 at 128. Supervising the router, which also adds route labels as a training signal, turns the deficit of the tied model against the dense block into an advantage.
Summary. The revised PDF adds the comparisons between chance and saturation (§R.2, §R.6, §R.9) and the measured certificate (§R.4), and reports what held on trained Transformers and what did not. The contribution is the theory: exact results, with complete proofs, on when local sharing gains survive composition and on what attribution requires. We hope this lets you reassess the paper.
Reply to Reviewer F8RX (1/2): Q1 and W1
Your main concerns are that the trained evidence sat at the two extremes and that the paper did not say how reliably its criteria predict final performance. The revised PDF adds comparisons between chance and saturation (Q1) and reports, level by level, what the theory predicted and what it did not (part 2); W1 states the scope of the claim.
Q1. Can the authors provide an end-to-end comparison in a non-saturated setting where both separate and shared models achieve meaningful but imperfect terminal accuracy?
Answer: yes, at 128 traces. Separate and shared experts reach 45.2% and 47.1% at horizon 8 and, in a new experiment, 80.2% and 83.5% at horizon 12. At 96 traces both are still near chance (3.2%), and at 192 both are near saturation.
The entries are final-output accuracy with learned routing. Horizon 8 is the paper's ten-seed study (Table 19); a rerun on different hardware gives 8.3 / 7.5 / 31.2%, 49.3 / 51.8 / 92.3% and 98.0 / 96.6 / 99.6%. Horizon 12 has five seeds (66 new runs), with budgets chosen by a rule fixed before the additional seeds were run (§R.9).
W1. The empirical task is too limited to establish broad practical impact; short-horizon models are nearly perfect and longer-horizon models are close to failure.
Answer. We agree that one family of symbolic tasks cannot establish broad practical impact, and the paper does not claim it: the abstract limits the trained evidence to "low-data symbolic settings", and the revised §8 now states this limit. The contribution is the theory; the experiments test it where its quantities are known. What carries over to an MoE without declared targets is a procedure: select a sharing choice on held-out data (Proposition 11), confirm it with the paired final-output audit (Proposition 45), and check routing before attributing a final-output deficit to sharing. In our models the sign of a resolved one-step gain was always inherited, so the audit mattered for the size of a gain and for unresolved contrasts. Within this setting we added:
The H12 and H16 results of Table 9 are length-extrapolation checks of models trained at shorter horizons. No claim rests on them, and the revised §G.3 says so.