- Rating
- 2(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2(+1)
Read review
Paper summary
This paper investigates soft-token feedback for parallel decoding in frozen pretrained diffusion language models (DLMs). The authors identify geometric limitations of Euclidean interpolation between the [MASK] embedding and a probability-weighted aggregate of predicted-token embeddings. They propose a training-free construction using spherical linear interpolation (SLERP), which controls angular displacement while preserving the norm of the [MASK] embedding.
The paper further studies how soft-token feedback modifies predictive distributions. It introduces an additive-mixture reference obtained by marginalizing over hypothetical discrete token realizations and compares this with a normalized multiplicative mixture. The observed predictions are closer to the multiplicative reference, motivating an agreement-seeking interpretation of soft-token feedback. Sequence-level consistency is evaluated using conditional reverse KL divergence between factorized parallel predictions and a sequential decoding reference.
Experiments on four pretrained DLMs and four mathematical reasoning and code-generation benchmarks report consistent improvements over Euclidean soft tokens and frequent improvements over vanilla parallel decoding. Additional analyses examine embedding geometry, interpolation choices, adaptive decoding, and sequence-level consistency.
The empirical findings are promising. However, the mathematical analysis does not establish that the improvements are specifically attributable to the proposed agreement-seeking mechanism rather than alternative explanations involving logit interpolation, effective interpolation strength, normalization, and prediction concentration.
Critical strengths
1. Strong empirical improvements under frozen-model decoding.
The method is evaluated across four pretrained DLMs, four benchmarks, and three parallel decoding rates. Table 2 reports improvements over Euclidean soft-token feedback in 46 of 48 settings, with ties in the remaining two. Improvements over vanilla decoding are also frequent. For example, on Dream/HumanEval at four tokens per step, accuracy increases from 17.68% (vanilla) and 23.78% (Euclidean) to 32.32%.
These results are practically interesting because the pretrained models remain frozen. They support the potential utility of continuous feedback for parallel decoding without additional training, even though they do not independently establish the proposed mechanism.
2. An interpretable construction with useful ablations.
The method separates angular interpolation from norm preservation. Let
The proposed construction applies SLERP between and , then scales the result to norm . This is a simple, mathematically interpretable design motivated by the observed angular separation between the [MASK] embedding and candidate aggregates.
The paper also includes comparisons with norm-matched linear interpolation, alternative output scaling, hyperparameter sensitivity, adaptive samplers, and single-token success recovery. These evaluations strengthen the empirical contribution, although they do not completely isolate the claimed geometric and probabilistic mechanisms.
Critical weaknesses
1. The proposed probabilistic mechanism is not mathematically identified by the reference-mixture and reverse-KL analyses.
Section 3 models uncertainty preservation through a latent discrete variable and defines
This is a valid marginalization under the assumed latent-variable model, but it is not a necessary consequence of uncertainty preservation through deterministic continuous embeddings. The construction assumes independent positionwise latent realizations, although the paper's motivation concerns dependencies among simultaneously predicted tokens.
Furthermore, the proposed SLERP representation is generally not the expected embedding under this model. That expectation would be
whereas SLERP interpolates normalized directions and subsequently rescales the output. No mathematical identity connects the additive reference to the proposed representation.
The multiplicative reference also admits a simpler explanation. Writing , we obtain
Thus, the multiplicative mixture is exactly softmax over averaged logits. Closer agreement with this reference does not uniquely identify an agreement-seeking mechanism; it may also reflect ordinary logit interpolation or changes in predictive concentration.
Appendix D.2 additionally includes the queried position among the discretized inputs, introducing a self-conditioning confound. The reference predictions may be influenced by explicitly supplying a candidate token at the evaluated position rather than by resolving dependencies across positions.
Finally, the reverse-KL analysis conditions both distributions on a restricted support . For factorized prediction and sequential reference ,
Because both distributions are renormalized, the reported divergence does not measure the unconditional probability assigned to coherent sequences. A reduction may also arise from mode concentration. Although Appendix D.3 acknowledges this limitation, the proposed mechanistic interpretation remains stronger than the evidence establishes.
These issues are consequential because the agreement-seeking explanation is presented as a central scientific contribution.
2. The geometric ablation does not isolate the claimed mechanism, and the supplementary configurations raise substantial reproducibility concerns.
Let , , and let denote the angle between their normalized directions. SLERP produces
However, the same direction is obtained by normalizing , where
Therefore, SLERP and normalized linear interpolation traverse exactly the same spherical arc for nondegenerate endpoints. Their difference is the parameterization of angular displacement, not the set of reachable directions.
Consequently, the same- comparison in Appendix B.2 does not isolate an intrinsically different interpolation trajectory. The performance difference in Table 5 could reflect a more favorable effective interpolation schedule rather than a distinct geometric mechanism.
More seriously, the supplied supplementary configurations appear inconsistent with Appendix A.2. The manuscript states that hyperparameters are fixed across benchmarks and parallel-decoding rates within each domain. However, inspection of dllm/metadata/*.json reveals that 26 of the 48 main-table configurations differ from these stated settings. Eight configurations use , although the reported search space is .
The supplied reproduction launcher also supports only SLERP configurations, and the included samplers reject non-SLERP interpolation modes. Consequently, the Euclidean baseline cannot be directly reproduced using the supplied implementation.
These findings do not establish that the reported results are incorrect, but they raise substantial concerns about hyperparameter selection, baseline comparability, and whether the experiments follow the stated protocol.
Finally, the main empirical comparisons lack paired uncertainty estimates. Several improvements are small relative to benchmark size, making their statistical reliability difficult to assess.
Overall, the empirical improvements are promising, but the mathematical analyses do not isolate the claimed mechanisms, and the configuration discrepancies weaken confidence in the central experimental comparisons.
Questions for authors
Q1. Mathematical justification of the probabilistic reference.
Section 3 assumes uncertainty-preserving feedback should correspond to
Why should this marginalization characterize uncertainty preservation for a deterministic continuous representation? Since SLERP generally does not equal the expected embedding under , can the authors provide a mathematical connection between the proposed representation and this reference? How would the interpretation change under correlated latent realizations?
Q2. Identifiability of agreement-seeking behavior.
The multiplicative reference is exactly equivalent to softmax over weighted-average logits. How do the authors distinguish agreement-seeking behavior from ordinary logit interpolation or predictive concentration?
Appendix D.2 also includes the queried position among the discretized inputs. Does the multiplicative preference persist when the queried position remains masked and feedback is restricted to other positions?
Q3. Exact relationship between SLERP and linear interpolation.
For nondegenerate endpoints, SLERP is exactly reproducible by normalized linear interpolation with an angle-dependent coefficient. Is the claimed advantage therefore uniform angular parameterization rather than a distinct interpolation trajectory?
Were the SLERP, norm-matched linear, and Euclidean baselines independently optimized over their effective angular displacements? What validation data and selection criterion determined the final hyperparameters?
Q4. Interpretation of restricted-support reverse KL.
Tables 4 and 8 report conditional reverse KL after renormalization on finite supports. What fractions of the original probability mass do the methods and sequential references assign to those supports?
Can the authors separate improved dependency modeling from concentration on a single preferred sequence? Reporting unconditional probability mass assigned to coherent and incoherent alternatives would be informative.
Q5. Discrepancies between the manuscript and supplementary configurations.
Appendix A.2 specifies domain-level hyperparameters fixed across benchmarks and parallel-decoding rates. However, the supplied metadata contains 26 of 48 configurations that differ from these settings, including eight instances of , outside the stated search space.
Were these configurations used to generate Table 2? If so, how were they selected, and on what validation data? How was test-set tuning avoided?
Furthermore, the supplied reproduction launcher and samplers support only SLERP interpolation. Can the authors provide the executable Euclidean and vanilla baseline configurations required to reproduce the main comparisons?
Q6. Statistical reliability and computational fairness.
Can the authors provide paired uncertainty estimates for the benchmark improvements, particularly where differences are small?
For adaptive decoding in Table 6, what are the measured forward-pass counts and wall-clock costs? Do the improvements persist under matched computational budgets?
5 comments
Rebuttal by Authors (2/3)
Q2-1. What does the multiplicative-reference comparison establish?
We define the multiplicative reference as the normalized weighted geometric mean of predictions induced by hypothetical discrete input realizations:
\frac{ \exp\left(\sum_z q(z\mid E)\log p_\theta(y\mid E,z)\right) }{ \sum_{y'} \exp\left(\sum_z q(z\mid E)\log p_\theta(y'\mid E,z)\right) }.$$ The geometric mean combines predictive distributions from separate model evaluations under different discrete input realizations. Since each component distribution is a softmax over its logits, the reference can also be written algebraically as softmax over weighted-average logits. This is a property of how the reference is constructed; it does not imply that the model’s prediction from a continuous soft-token input is computed by combining predictions from discrete input realizations in this way. ### **Q2-2. Does the multiplicative preference persist when the queried position remains masked?** The multiplicative reference remains closer to our method when the queried position is kept masked and feedback is restricted to the other positions. Table 1 reports the mean JS divergence to the additive and multiplicative references of LLaDA. With the queried position masked, the divergence to the multiplicative reference is 0.0737, compared with 0.1989 for the additive reference. This preserves the same qualitative preference observed with full evidence. **Table 1. Mean JS divergence to the additive and multiplicative references under full evidence and with the queried position masked. Lower values indicate greater similarity.** | Evidence setting | Additive reference | Multiplicative reference | |---|---:|---:| | Full evidence | 0.2099 | 0.0410 | | Queried position masked | 0.1989 | 0.0737 | ### **Q3. Exact relationship between SLERP and linear interpolation** SLERP and normalized linear interpolation follow the same spherical arc for nondegenerate endpoints. At the same numerical $\lambda$, they generally reach different points on that arc: SLERP makes $\lambda$ the fraction of angular displacement, whereas the effective angular displacement under normalized Euclidean interpolation depends on $\lambda$ and the endpoint norms. The norm-matched linear baseline in Table 2 normalizes the Euclidean interpolant to the [MASK] norm. Its comparison with SLERP therefore tests the interpolation parameterization at the same numerical $\lambda$, rather than a different path or set of reachable directions. We will describe the result accordingly: the ablation supports the benefit of SLERP’s angular parameterization under the tested settings. Appendix A.2 specifies the search grid and the final settings fixed across benchmarks and parallel-decoding rates within each domain. **Table 2: Effects of interpolation and output norm on accuracy (%)** | Model | Benchmark | [MASK] norm with SLERP | Candidate norm with SLERP | [MASK] norm with Linear | |---|---|---:|---:|---:| | Dream | MATH-500 | **22.40** | 21.20 | 16.40 | | Dream | HumanEval | **50.61** | 50.00 | 50.00 | | LLaDA | MATH-500 | **23.60** | 22.60 | 21.80 | | LLaDA | HumanEval | **45.12** | 41.46 | 42.07 | | LLaDA 1.5 | MATH-500 | **24.00** | 21.80 | 21.20 | | LLaDA 1.5 | HumanEval | **43.90** | 39.63 | 37.80 |Rebuttal by Authors (3/3)
Q4-1. Probability mass retained on the restricted support
For each target, we construct the restricted support as the union of the top-10 candidate sequences from the distributions being compared. Table 3 reports the average probability mass each distribution assigns to this support before renormalization. The support captures most of the probability mass for all three distributions in both datasets.
Table 3. Mean probability mass assigned to the shared top-10 support, averaged over targets.
| Dataset | Soft method | Additive reference | Multiplicative reference |
|---|---|---|---|
| GSM8K | 99.91% | 99.75% | 99.85% |
| Math500 | 97.68% | 97.06% | 97.41% |
Q4-2. How can improved dependency modeling be distinguished from concentration on a single preferred sequence?
We use reverse KL as a proxy for whether the factorized prediction concentrates probability on sequence combinations supported by the dependency-preserving sequential reference. Specifically, we measure , where is the factorized prediction and is the sequential reference, both normalized on the shared support. This direction has a mode-seeking asymmetry: it penalizes for assigning probability to sequences that considers unlikely, while not requiring to cover every mode of . Thus, lower divergence indicates that the prediction’s probability mass is better aligned with sequences supported by the reference.
Table 4 shows that our method has the lowest reverse KL for all four models, indicating closer alignment with the sequential reference than either vanilla parallel decoding or the Euclidean baseline.
Table 4. Reverse KL divergence from the factorized joint prediction to the dependency-preserving sequential reference.
| Model | Vanilla | Euclidean | Ours |
|---|---|---|---|
| LLaDA | 2.1989 | 0.3415 | 0.2458 |
| LLaDA-1.5 | 2.0327 | 1.9273 | 0.5624 |
| LLaDA-2.0 mini | 2.7338 | 1.5610 | 1.1739 |
| Dream | 4.2733 | 4.1139 | 1.7553 |
Q5. Hyperparameter selection and baseline reproducibility.
We use the settings specified in Appendix A.2. As in Section B.3, the method also performs consistently across a broad range of parameter values, indicating that its performance is not highly sensitive to the choice of and . We therefore selected the values of and from this stable range. The Euclidean and vanilla baselines are run by changing the mode from slerp to linear and vanilla in the configuration. This makes the baselines executable within the submitted implementation.
Q6-1. Paired uncertainty for the benchmark where the improvement differences are small?
For LLaDA-1.5 on MBPP with 8 tokens per step, the paired bootstrap 95% confidence interval for the accuracy difference (SLERP − Linear) is percentage points. The exact McNemar test gives . The interval includes zero, and the paired test finds no statistically detectable difference in this setting. The analysis compares both methods on the same benchmark examples; because decoding is greedy, there is no decoding-seed variability.
Q6-2. Computational budget for adaptive decoding methods.
For LLaDA on HumanEval, adaptive decoding with our feedback required an average of 120.5 forward passes per problem (median 118.5; range 59–191). This is approximately 76.5% fewer passes than the configured 512-step baseline. The average wall-clock time across the 164 HumanEval problems was 1,647.5 seconds (27.5 minutes), or about 10.0 seconds per problem.
References
[1] Chan and Darwiche. On the revision of probabilistic beliefs using uncertain evidence. IJCAI 2003
[2] Munk et al. Uncertain evidence in probabilistic models and stochastic simulators. ICML 2023
Rebuttal by Authors (1/3)
We sincerely thank Reviewer C2iV for their thoughtful and constructive review. We are especially grateful that the reviewer clearly acknowledged the contributions of our paper, including the proposed training-free soft-token method and our analysis on why soft tokens improve the parallel decoding. We believe that our paper makes the first attempt at analyzing why soft tokens improve parallel decoding in diffusion language models and can meaningfully contribute to the community. Below, we provide point-by-point responses to all questions and concerns raised. All the comments are constructive and help strengthen our work.
Q1-1. Why use an additive mixture to formalize uncertainty preservation?
A canonical way to formalize uncertainty preservation over hypothetical discrete input states is to assign a probability distribution to the possible states and propagate it through the model by marginalization. This is the standard uncertain-evidence formulation discussed in prior works [1, 2]. We apply this formulation to soft-token feedback: each soft token represents uncertainty over the unresolved [MASK] state and its top-k candidates, and the model’s prediction is averaged over the resulting discrete input realizations.
Specifically, at position j, we assign probability 1−λ to [MASK] and probability λpˉj,i to candidate vj,i. Under the factorized joint distribution q(z∣E)=∏jqj(zj∣E), marginalization gives
padd(y∣E)=∑zq(z∣E)pθ(y∣E,z).
This defines the additive reference for this particular uncertain-evidence interpretation. It is a predictive-level reference for testing that interpretation, not a necessary consequence of every deterministic continuous representation.
Q1-2. Relationship between the additive reference and SLERP
The additive reference and our construction use the same positionwise candidate weights, but operate at different levels. The additive reference averages model predictions over discrete input realizations, whereas our method maps the candidate information to a single continuous embedding using SLERP to control its direction and preserve the [MASK] norm.
We do not claim that the SLERP embedding is the expected embedding under q. At a single position, that expectation would be
E[eZj∣E]=(1−λ)eMASK+λ∑ipˉj,iej,i.
SLERP generally differs from this expected embedding. Moreover, even if the expected embedding were used as the model input, its prediction would not generally equal the additive reference: the model’s nonlinear transformations mean that a prediction from an expected input need not equal the average of predictions from discrete inputs. We therefore use the additive reference as a predictive-level comparison, not as a formula that determines the SLERP construction.
Q1-3. How does the interpretation change under correlated latent realizations?
Our reference uses a factorized distribution over hypothetical input states. This means the latent state assignments are independent under the reference distribution; it does not assert that actual token dependencies are absent. A correlated reference would instead require specifying a non-factorized joint distribution q(z∣E), representing uncertainty over joint configurations across positions. The marginalization formula would remain unchanged, but the weights assigned to those configurations would differ. Such correlations are not determined by the positionwise candidate probabilities or by the deterministic soft-token embedding alone, so defining a correlated reference would require an additional modeling assumption.