- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
- Proposes a method to accelerate text generation while watermarking without compromising watermark detection reliability or generation quality.
- To overcome the limitations of the existing single-sequence estimation approach, a tree-structured draft is constructed, and multiple candidates are verified simultaneously through deterministic vocabulary partitioning.
Critical strengths
- The paper is generally well written.
- The claim of accelerating generation speed is interesting, and the rationale behind this claim appears to be well justified.
Critical weaknesses
- Although the proposed method improves watermark generation speed, it appears that the detection performance (TPR) decreases as generation speed increases. This raises concerns about whether the improvement in generation speed sufficiently justifies the reduction in detection performance.
- While the paper demonstrates improvements in watermark generation speed, the detection speed is not reported. Evaluating detection latency would provide a more comprehensive understanding of the computational efficiency of the proposed method.
- Although the proposed method improves generation speed, it is unclear whether the generated text maintains its quality. If text quality degrades, the presence of a watermark may become more noticeable to users. Therefore, reporting text quality metrics, such as Perplexity (PPL), would help assess whether the proposed method achieves faster generation without compromising text quality.
Questions for authors
- The questions are the same as those raised in the Weaknesses section.
3 comments
Thank you for the detailed responses and additional experiments. The detection-time measurements show that detection cost is essentially unchanged across k, and the log-perplexity results, together with Theorem 3.1, show that text quality is preserved. These address my concerns on W2 and W3. I also acknowledge the quantified trade-off and the concrete recommendation for the choice of k.
However, my concern about the speed–detectability trade-off (W1) remains. The long-form experiment shows that the gap to k=1 shrinks as the text grows from 200 to 600 tokens, but this is largely expected: TPR saturates for every k once enough tokens are observed, so the result does not show that the per-token loss of watermark signal is reduced. The loss remains at short lengths, where detection is hardest. A comparison in terms of the additional tokens required to match the TPR of k=1 would be more informative.
The same loss is also visible under token edits. In Figure 9, k=2 stays close to k=1, but the gap for k=4 becomes noticeably larger under substitution and deletion than in the clean setting, and k=3, which the response recommends when more acceleration is desired, is not reported in Figure 9 or Table 8. In addition, Table 8 shows decreases in signal retention for Gumbel-max whose confidence intervals do not overlap (e.g., deletion at ρ=0.2: 0.528, 0.493, 0.492 for k=1, 2, 4), which is not fully consistent with the claim of no robustness loss. Taken together, the setting in which detectability is reliably preserved appears to be k=2, where the acceleration is modest; with the EAGLE-style drafter, the response itself notes that most of the throughput gain comes from the lighter drafter and that the tree adds up to 1.18× on top.
Overall, I acknowledge the additional experiments and the improved evidence on detection cost and text quality. However, the remaining concern about whether the achievable speedup justifies the loss of detectability, particularly for short or edited texts, prevents me from raising my score.
Clarification on the Remaining Concern
Thank you for the follow-up, and we are glad that our responses have addressed your concerns on detection cost (W2) and text quality (W3).
On the remaining trade-off (W1). We acknowledge that our method has a limitation for short texts at larger , where a detectability gap remains. However, we believe this limitation does not negate the contribution of our work, which is two-fold:
- Acceleration. Vocabulary partitioning provably improves sampling efficiency and throughput over single-sequence decoding for any partition and any drafter (Thms. 3.2–3.3), without additional draft models.
- Detectability under multi-branch drafting. Vocabulary partitioning prevents severe detection loss: without it, tree-based watermarked decoding suffers from -way source ambiguity, and detection degrades sharply, as shown in our ablation. Partitioning decreases this ambiguity to 2 and restores detectability. For the same reason, the EAGLE head would also suffer severe detection loss without partitioning. With partitioning, its TPR at is no lower than Seq.
Neither contribution depends on short texts at large . That setting only determines how should be chosen: for short texts, a small is recommended, while for long-form generation, where acceleration matters most, a larger provides additional speedup with almost no loss in detectability.
As suggested, we will also include in the robustness experiments in the revised version.
In short, we acknowledge this limitation of our method, but we do not believe it diminishes either of these two contributions.
Response to Reviewer vJvV
W1. Speedup vs. detectability
Thank you for raising this point. In short, the detectability change is small for moderate branching factors and vanishes for long texts, while generation quality (W3) and detection cost (W2) are unchanged. We elaborate below:
Based on these results, we recommend k=2 when detectability is the priority (e.g., short texts) and k=3 when more acceleration is desired, especially for long-form generation.
W2. Detection speed is unaffected
Thank you for raising this point. We note that detection is typically performed offline and only once per text, so it does not affect generation latency. Moreover, detection requires no model forward pass: it only reconstructs the pseudorandom variables from the text. Compared with single-sequence decoding (k=1), our method adds one lightweight hash per token to identify the subset containing that token; all other computations are unchanged.
We add a new experiment to measure the detection time per 200-token text (Llama, QA; 100 texts per setting; mean in ms, standard deviation in parentheses):
This result shows that the detection time of our method is nearly identical to that of k=1, so our method improves generation speed without affecting detection efficiency.
W3. Text quality is preserved
Thank you for raising this point. We address it from both theoretical and empirical perspectives.
For all k, the log-perplexity of our method closely matches that of Base, confirming that generation quality is preserved under our acceleration.