- Rating
- 4(+2)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies the confidence shortcut, showing that confidence sometimes selects answers for which the model has enough information, but sometimes the model may choose a position it does not know how to answer yet and fill it with something that only looks like a plausible answer. It also gives a deep analysis of order selection and shows that random masking has some advantages, because confidence-based selection may be biased, and training around the selected order may make things worse.
Critical strengths
-
Comprehensive experiments. The paper includes controlled training experiments across several reasoning tasks and an evaluation of LLaDA-8B Base. This helps show that the observed failure is not limited to a single small model or experimental setting.
-
Showing the value of random-mask training. The results suggest that standard random-mask training can be more robust than confidence-aligned training on difficult reasoning tasks. I think this is a useful message to the community, as reducing training–inference mismatch may not always improve performance when the decoding policy itself is suboptimal.
Critical weaknesses
My main concern is whether the paper provides enough new insight beyond existing work on generation order. Zhang et al. (2026) already study addition, carry dependencies, and different generation orders.
The analysis of premature commitment and the effects of confidence-aligned training adds useful observations, and I find the results supporting random-mask training interesting. For models trained with random masking, why does changing to a task-specific reference order help on addition and Maze, but not consistently on ListOps and Countdown? I think a clearer analysis of when order selection is the bottleneck would help connect these experiments.
I would be interested in seeing whether mixing standard random-mask training into PUMA could recover performance. Would a small proportion of random-mask training be enough, and would the improvement appear under confidence decoding or only under the reference order? This could help clarify the value of broader training-context coverage.
Reference
Zhang, S., Yu, L., Brekelmans, R., Tang, L., Asif, S., and Ver Steeg, G. (2026). Generation Order and Parallel Decoding in Masked Diffusion Models: An Information-Theoretic Perspective. arXiv:2602.00286.
Questions for authors
- Section 4 is hard to follow. I think Section 4 could be organized by the findings rather than by dataset. For example, the authors could group the experiments into:
- Cases where changing the decoding order recovers performance.
- Cases where a training gap remains even after changing the order.
- Cases where confidence-aligned training helps. A summary table would make it easier to understand what each experiment contributes to the main claims.
2.Additional remasking comparison. I think the analysis of remasking could go deeper. Although the paper evaluates ReMDM and PRISM, it would be useful to also include WINO (Hong et al., 2025), which uses bidirectional context to identify and remask suspicious tokens. This comparison could help clarify whether the observed failures persist across different error-detection and remasking strategies.
Reference Hong, F., et al. (2025). Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMs. arXiv:2507.18578.
3 comments
Thank you for the detailed response and the new experiments. I think this paper provides new insight into what random-mask training contributes. Random masking is usually viewed as a source of train–inference mismatch, and many recent papers try to close this gap with confidence-aligned training or self-distillation. This paper shows that the broad context coverage of random masking is valuable in itself, and that removing the mismatch can hurt.
My remaining concern is the presentation and flow of the paper. I encourage the authors to keep improving it in the final version. Given the new insights, I am raising my score to 3.
Thank you for recognizing our contribution and for your positive reassessment. We appreciate your emphasis on our key finding: broad context coverage during training is valuable in itself, and reducing train–inference mismatch can hurt reasoning performance. We will further improve the presentation and flow in the final version to make this message and how it connects our results across tasks even clearer.
Response to Reviewer FJnB
Thank you for the constructive suggestions on related work and additional experiments, which shaped the new Section 3 and Table 5.
We identify a regime where confidence's advantage reverses, then show how aligned training amplifies the failure.
Zhang et al. [1]: On addition with ≤10-digit operands, confidence outperforms R2L under parallel decoding with pretrained LLaDA-8B-Instruct. Their difficulty groups vary operand length; the edge-case score combines overflow cascades (9,999,999,999+1) with cases such as A+0. They train AR arithmetic models but compare MDM decoders with frozen LLaDA weights.
Our controlled comparison: Even under single-token decoding, fixing 32-digit operands and varying carry span—including chains ending at internal digits—reveals a systematic confidence shortcut. While chain digits remain masked, the model substitutes the chain head's local outgoing carry for its unresolved incoming carry, causing ±1 errors when they differ (§4.3). Matched Random/PAPL/PUMA training shows that alignment amplifies this bias. LSD-first recovers Random/PUMA accuracy and improves frozen LLaDA-8B (§4.4; Table 5).
Difficult reasoning is precisely where order should help. CoT and test-time computation are valuable because intermediate results make hard predictions tractable. Our controlled sweep asks whether confidence organizes the computation that the same model can perform under a dependency-following order (§3).
[1] Zhang et al., Generation Order and Parallel Decoding in Masked Diffusion Models: An Information-Theoretic Perspective, 2026.
Table 5 now organizes the tasks by what order and training change:
Layered ListOps and sequential Countdown expose natural intermediate steps, while leaving scheduling or arithmetic choices unresolved. Their optimality is unnecessary for comparing training schemes under the same decoder. The results favor preserving broad training contexts and improving how inference uses them.
Mixing is sensitive to its ratio, and switching objectives does not readily reverse PUMA's learned behavior. Following your suggestion, we added static mixing (300k updates) and continuation (+100k).
Random–PUMA mixing on Addition: confidence / LSD-first exact match, by minimum carry length (Table 16).
Effect of 100k continuation updates on long-carry Addition (≥28; Table 17).
The 25% mixture fails to converge within the budget, while 50% recovers Random-level accuracy with the overhead of maintaining PUMA trajectories. After PUMA training, 100k random-mask updates give no recovery under confidence; the reverse switch weakens Random. LSD-first stays at 1.000 throughout. This suggests that confidence-aligned training can settle into behavior that is hard to change later, favoring random masking from the start.
WINO-single gives up parallel drafting and retains verification to recover Random/PUMA accuracy. We added WINO and its single-token variant alongside PRISM and exact LOO (Appendix E.3).
Remasking and correction on Addition: exact match at minimum carry length 28 (Table 15).
PRISM/WINO partially repair PUMA; single-token drafting brings WINO to the accuracy of exhaustive LOO correction, while retaining verification. Exact LOO itself uses 33 queries per round. PAPL remains below 0.04 across these strategies: stronger verification does not remove its conditional-prediction deficit. Maze errors likewise resist revision because neighboring wrong labels can support one another, whereas DEF builds the solution through successive eliminations.