- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes Sonar, a training-free sampling method for masked diffusion language models. It aims to improve reasoning diversity by measuring spectral overlap among candidates’ contextual token representations and using this signal to steer generation.
Critical strengths
-
Distinctive design: Sonar uses the spectral geometry of contextual token representations to guide candidate diversity. It measures diversity at the final layer while applying steering at an intermediate layer.
-
Training-free approach: The method keeps pretrained model parameters fixed and requires no additional model training.
Critical weaknesses
-
Task- and temperature-dependent gains: Sonar’s advantage over ODD varies across tasks and temperatures. Although it achieves substantial gains in some low-temperature settings, its advantage on GSM8K is inconsistent, and for Dream it shrinks or reverses at higher temperatures.
-
Unclear computational trade-off: Sonar requires backpropagation through transformer blocks and additional forward evaluations. The paper does not quantify this overhead relative to ODD or provide compute-matched comparisons, leaving unclear whether the performance gains justify the additional computation.
Questions for authors
-
Could the authors explain why Sonar’s advantage over ODD shrinks or reverses at higher temperatures for Dream?
-
Could the authors report success-versus-compute curves for Sonar, ODD, and ordinary sampling, allowing the baselines to generate additional candidates within the same compute budget?
5 comments
(w2,q2)
W2 / Q2. Computational efficiency under comparable inference budgets
We agree that computational efficiency should be evaluated under comparable inference budgets, allowing baselines to generate more samples. As also emphasized by Reviewer B9mR, evaluating multiple generation settings provides a more comprehensive picture of each method's exploration potential. Different temperatures and diversity strengths may discover complementary solutions, so relying on a single configuration could underestimate a method's capabilities.
Following this, we selected mixtures of settings for LLaDA, ODD, and SONAR through independent hyperparameter searches on a small subset of problems, maximizing their combined problem coverage on this subset. We allow the baselines to generate substantially more candidates to account for SONAR's additional overhead.
To reduce SONAR's overhead, we use interventions closer to the output. Our measurements show that 1-block and 4-block interventions require 1.85× and 2.12× the runtime of ordinary LLaDA, respectively, compared with 3.97× for the original 16-block intervention used in the submitted manuscript. (See table R4 and appendix F2)
Experimental settings.
- LLaDA: 6 settings combining temperatures and sample allocations, totaling 144 samples per seed.
- ODD: 9 settings combining temperature and diversity step size, totaling 144 samples per seed.
- SONAR: 4 settings (two 1-block and two 4-block intervention profiles), totaling 64 samples per seed.
The resulting relative GPU-time budgets are 1.00× for LLaDA, 1.08× for ODD, and 0.88× for SONAR. Thus, SONAR uses less compute than either baseline.
We measure exploration performance using Coverage@M (Sec. 5.2, Fig. 4), which reports the expected number of unique problems solved when combining (M) independent seed trials.
Table R10. Coverage@M under mixed settings and comparable computational budgets.
| Method | M=1 | M=2 | M=4 | M=8 | Relative GPU budget |
|---|---|---|---|---|---|
| LLaDA (144 samples/seed) | 102.875 ± 1.053 | 112.036 ± 1.569 | 121.514 ± 1.803 | 129 | 1.00× |
| ODD (144 samples/seed) | 111.750 ± 2.634 | 119.607 ± 2.241 | 127.200 ± 1.564 | 133 | 1.08× |
| SONAR (64 samples/seed) | 109.500 ± 3.240 | 121.179 ± 3.163 | 132.029 ± 2.268 | 143 | 0.88× |
Although ODD performs better for a single seed, SONAR achieves higher coverage as exploration extends across multiple seeds. At (M=8), SONAR solves 143 problems, compared with 133 for ODD and 129 for LLaDA, while using less GPU time and generating only 512 samples versus 1,152 for each baseline.
Furthermore, SONAR discovers solutions to 14 problems missed by extensive LLaDA sampling, compared with 8 for ODD. Even combining both baselines (2,304 samples), SONAR discovers 9 problems that neither baseline solves, despite using approximately 2.4× less GPU time.
These results demonstrate that SONAR can achieve greater problem coverage under a smaller computational budget, while also uncovering reasoning modes missed by extensive conventional sampling.
For a detailed computational analysis, including inference latency, GPU memory, and forward/backward operations, please refer to Table R4 in our response to Reviewer B9mR and Appendix F.2–F.3.
Thank you again for your constructive review. If you feel our clarifications have successfully addressed your questions and concerns, we kindly ask that you consider raising your score.
follow up
Thank you again for your constructive review and feedback. Following your observations, we expanded our GSM8K experiments across sampling temperatures and diversity strengths, obtaining improved results on both LLaDA and Dream. We also conducted additional matched-compute comparisons against LLaDA and ODD. We hope these results address your concerns and would welcome any further questions or feedback before the discussion period ends.
Summary and (w1,q1)
We thank reviewer g17K for their constructive feedback and for recognizing SONAR's distinctive design and training-free approach to representation-space exploration.
We address the reviewer's concerns through additional experiments and analyses, summarized below:
W1 / Q1. Task- and temperature-dependent gains
The reviewer observes that SONAR's gains over ODD vary across temperatures and models. We believe that a diversity method need not outperform other methods at every sampling temperature. The goal is to improve the method's overall ability to discover alternative reasoning modes under suitable exploration settings. Performance at other temperatures reflects the interaction between sampling stochasticity and the method's exploration bias.
Temperature introduces stochasticity into token sampling, whereas SONAR explicitly guides exploration through a geometric bias defined by its diversity metric. Our hypothesis is that this bias can exploit the structure learned in the model's representation space to discover overlooked reasoning modes. How effectively this bias interacts with temperature depends on the representation structure learned by each model. Intuitively, lower temperatures may complement stronger geometric diversification, but this need not hold across all models and tasks.
Our initial experiments explored a limited range of settings. Following the reviewer's observation, we expanded our hyperparameter search over sampling temperature and diversity strength. This identified more effective configurations for GSM8K (e.g., T=0.25 for Dream and T=0.5 for LLaDA). The revised results strengthen SONAR's performance, particularly at lower temperatures.
Table R9. Updated results on GSM8K. Values are reported across low, medium, and high sampling-temperature settings (low / medium / high).
On GSM8K, both methods benefit from stronger diversification. ODD achieves its best results with larger diversity step sizes (64 and 128), similar to SONAR's improvement with stronger diversity settings. The key difference is that ODD benefits from higher sampling temperatures, whereas SONAR performs better at lower temperatures. Neither behavior is inherently better or worse. Rather, this reflects how the different exploration biases of the two methods interact with sampling stochasticity and the representation structure learned by each model. Please refer to Table 1 and Figure 4 in the revised manuscript for the updated results.