- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes dVoting, a training-free test-time scaling method for diffusion language models. It preserves tokens that agree across sampled responses, regenerates the remaining positions using entropy-threshold parallel decoding, and aggregates candidate answers through majority voting with early stopping. Experiments on LLaDA-8B-Instruct, Dream-7B-Instruct, and LLaDA-1.5 demonstrate improvements over single-generation baselines and favorable accuracy-cost tradeoffs across mathematical reasoning and question-answering benchmarks. The principal contribution is cross-sample token reuse to reduce the cost of obtaining additional votes.
Critical strengths
dVoting offers a simple, training-free way to exploit arbitrary-position regeneration in diffusion language models, with practical benefits supported across multiple backbones and benchmarks. The end-to-end measurements are particularly useful: on GSM8K at generation length 256, it achieves 83.78% accuracy in 38.3 seconds, compared with 82.33% in 96.8 seconds for majority voting. The remasking ablations and evaluation on an RL-enhanced model further support its potential as an inexpensive inference-time improvement.
Critical weaknesses
- The comparisons do not sufficiently isolate the proposed contribution. dVoting uses adaptive entropy-threshold decoding, whereas the main voting baselines use fixed denoising budgets. Adaptive stopping and entropy-based acceleration already have precedents, making controlled attribution essential. Table 7 is helpful, but the MATH500 gain over confidence-based remasking is only 0.4 percentage points while requiring more steps, without uncertainty estimates. Matched-decoder and matched-budget comparisons are needed to establish the value of cross-sample consistency.
- The central reuse mechanism is insufficiently validated and specified. Fixing tokens after agreement between two samples makes later votes dependent on earlier outputs and may preserve shared errors. NUPR establishes repetition, but does not establish that freezing those tokens preserves useful exploration. The paper provides no systematic analysis of error persistence or diversity loss, while Algorithm 1 leaves competing repeated-token choices unspecified and does not clearly explain the illustrated stopping after two matching answers.
Questions for authors
- Under identical entropy thresholds, temperatures, block sizes, and hardware allocation, how does dVoting compare with independent sampling plus answer-based early stopping at matched latency? Please include repeated-run uncertainty estimates.
- Which token is retained when multiple token values each occur at least twice at the same position? Can preserved tokens subsequently change? Also, with n=5, Algorithm 1 requires three matching answers; what explains Appendix B’s stopping after two samples?
- How often does token reuse lock in an incorrect answer or prevent a correction achieved by independent sampling? Please quantify this alongside answer diversity, and clarify whether NUPR excludes padding and end-of-sequence tokens.