- Rating
- 4(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper introduces an alternative to standard DLLM training which treats all unmasking orders as equally plausible with it's standard ELBO objective being equivalent to Any Order training. The proposed method MAPLE is a "middle ground" of sorts which uses models the sequence as a dependancy graph where edges are formed between the prerequisite tokens and their dependants, where tokens that are not connected, could be unmasked in any order potentially, thus modelling dependancies within a sequence and still allowing for many different orderings and parallel decoding oppurtunities. The paper also derives a new ELBO which accounts for both this position selection and token selection from standard ELBO. The paper is well motivated and expeirmental results on finetuning of LLaDA 2.0 and DreamReasoner show the efficacy of this new loss over representative baselines.
Critical strengths
-
The approach is well motivated, and the paper explains its main ideas clearly. The examples are particlarly helpful in illustrating why revealing supporting information before dependent tokens can improve generation.
-
The results on mathematical reasoning and code generation are strong overall. Improvements across two model families and several benchmarks show promising evidence that the approach is effective and generalisable.
Critical weaknesses
-
Missing comparison with [1] which addresses a closely related problem, it is briefly discussed in the introduction but the paper does not compare against it experimentally. It would be good to know if MAPLE's more complicated DAG formulation beats a simpler confidence based one.
-
It is unclear which component produces the gains. MAPLE changes both how the training contexts are sampled and how confidence is supervised. It would be nice to see these changes ablated seperately so that it would be clear how much each change helps.
-
The paper does not compare teacher-derived graphs against random graphs or simple ordering rules. Such comparisons would show whether the gains come from useful dependency information or merely from restricting reveal orders. An empty graph baseline is not sufficient in this case.
[1] Peng, F. Z., Bezemek, Z., Rector-Brooks, J., Zhang, S., Zhang, A. R., Bronstein, M., Tong, A., & Bose, A. J. (2026). Planner Aware Path Learning in Diffusion Language Models Training. International Conference on Learning Representations (ICLR)
Questions for authors
Please address the weakenesses above. I would be happy to increase my score based on the author's response.
After Rebuttal
The authors have provided additional results that have addressed the concerns regarding the ablations, comparison to PAPL and the simple graph baselines. Therefore I have increased my rating from a 3 to a 4.
4 comments
Response to Reviewer jZ7M (2/2): component ablation and graph ablation
W2. It is unclear which component produces the gains. MAPLE changes both how the training contexts are sampled and how confidence is supervised. It would be nice to see these changes ablated separately…
Setup. The dependency graph enters MAPLE's objective (Eq. 15) through three components:
- State sampling: the training contexts are sampled along the graph.
- Token-loss expectation: the token loss puts more weight on graph-ready positions.
- Position-selection KL: the confidence is supervised toward graph-ready positions.
We retrain LLaDA 2 on FineCode with every combination, following the same setup as described in Section 6 and Appendix B. A component marked ✗ falls back to its any-order form: uniform state sampling, uniform token-loss weighting, or no KL.
| Variant | State sampling | Token-loss expectation | Position-selection KL | HumanEval | MBPP | LCB Pro | Spider | Avg. |
|---|---|---|---|---|---|---|---|---|
| MAPLE (full) | ✓ | ✓ | ✓ | 84.15 | 81.71 | 4.96 | 51.06 | 55.47 |
| − state sampling | ✗ | ✓ | ✓ | 83.54 | 78.99 | 4.39 | 47.78 | 53.67 |
| − token-loss expectation | ✓ | ✗ | ✓ | 81.10 | 79.38 | 3.97 | 49.61 | 53.51 |
| − KL | ✓ | ✓ | ✗ | 82.32 | 80.16 | 4.53 | 49.90 | 54.23 |
| only state sampling | ✓ | ✗ | ✗ | 81.10 | 79.77 | 3.68 | 48.94 | 53.37 |
| only token-loss expectation | ✗ | ✓ | ✗ | 84.15 | 79.77 | 4.11 | 45.65 | 53.42 |
| only KL | ✗ | ✗ | ✓ | 81.71 | 76.26 | 3.97 | 42.36 | 51.07 |
| Any-order | ✗ | ✗ | ✗ | 82.93 | 77.04 | 4.53 | 40.43 | 51.23 |
All three components help.
- Each one is needed: removing any one of them lowers the average by 1.2–2.0 points.
- They are complementary: no single component reaches the full recipe (51.07–53.42 vs. 55.47).
- The two changes named in the review: "how the training contexts are sampled" corresponds to state sampling, and "how confidence is supervised" to the KL. Removing the first lowers the average by 1.8 points, and removing the second by 1.2 points.
Full MAPLE is best or tied-best on all four benchmarks. All variants decode at similar parallelism on every benchmark (tokens per forward within about 5% of each other).
Revision: we have added this table as Appendix J.1, with a summary in Section 6.4.
W3. The paper does not compare teacher-derived graphs against random graphs or simple ordering rules. Such comparisons would show whether the gains come from useful dependency information or merely from restricting reveal orders. An empty graph baseline is not sufficient in this case.
Setup. We keep MAPLE's objective and replace the teacher graph on LLaDA 2 / FineCode by:
- A degree-matched random graph: every token keeps the number of parents it has in the teacher graph, but its parents are drawn at random among earlier tokens.
- Simple ordering rules: a strict chain (each token's parent is the previous token, i.e., left-to-right order) and a group chain (left-to-right order in groups of three consecutive tokens).
The graph changes how parallel the trained model decodes at a given confidence threshold. A chain, for instance, trains a nearly sequential decoder. We therefore compare all graphs at the same parallelism: the table below reports accuracy at 3 tokens per forward.
| Training graph | HumanEval | MBPP | LCB Pro | Avg. |
|---|---|---|---|---|
| Teacher dependency graph (MAPLE) | 83.12 | 78.09 | 4.96 | 55.39 |
| Degree-matched random graph | 82.67 | 74.80 | 3.97 | 53.81 |
| Group chain | 51.87 | 55.09 | 0.57 | 35.84 |
| Strict chain† | 71.95† | 69.26† | 1.84† | 47.68† |
| Empty graph (any-order) | 79.85 | 74.77 | 4.53 | 53.05 |
† The strict chain does not reach 3 tokens per forward on any benchmark: even at a confidence threshold as low as 0.1, it decodes only about 1.1 tokens per forward. The reason is that a strict chain makes only one position ready at a time, the next token, so the model learns to be confident about that position alone. Its row reports the accuracy at the 0.1 threshold.
The gains come from the dependency information. The teacher graph is the best on all three benchmarks, ahead of the random graph and of both ordering rules.
- Random graph: with the same in-degrees but random parents, accuracy drops on all three benchmarks, and the average falls from 55.39 to 53.81.
- Simple ordering rules: the group chain reaches 35.84. The strict chain reaches 47.68 while decoding only about 1.1 tokens per forward.
Revision: we have added this table to the main text as Table 4 (Section 6.4), with the construction of each graph in Appendix J.2.
We hope these results address all three points. We are happy to provide further details.
Thank you for the additional results based on the questions I had, and they have addressed my concerns. As a result I have increased my score to a 4.
Thank you
We are glad that our response has addressed your concerns, and we greatly appreciate your constructive feedback!
Response to Reviewer jZ7M (1/2): comparison with PAPL
Thank you for the encouraging assessment and the concrete suggestions! We ran all three requested experiments, with the same setting as Table 1 (see Appendix B for hyperparameter details).
Setup. We train PAPL on LLaDA 2, on FineMath and on FineCode, following the experimental setup described in Section 6 and Appendix B. We use the loss recommended in its official repository, NLL⋅[1+sg(e−NLL)].
MAPLE outperforms PAPL. It is better on seven of the eight benchmarks and ties on AMC12, and its average is 4.3 points higher. This is consistent with Table 1: the order-aware baselines, now including PAPL, stay within 1.3 points of any-order on average (51.90–53.99 vs. 52.71), while MAPLE reaches 56.88.
Why the DAG helps beyond confidence. PAPL belongs to the same family as PUMA and TRIMS in Table 1. Their order signal is one score per position: PAPL and PUMA use the model's own confidence, and TRIMS uses a teacher's token difficulty. Such a score tells how easy a token is to predict, but not which earlier tokens it depends on. MAPLE supervises exactly these pairwise relations (Section 5): a position is ready only once all of its prerequisite tokens are revealed.
To illustrate the benefit of this dependency information, consider a reasoning sequence that contains the step "6 × 2 = 12". The result "12" depends on its operands "6" and "2".
Revision: we have added PAPL to Table 1 and Section 6.1, with its setup in Appendix B.4.