- Rating
- 3
- Confidence
- 1
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper introduces DLM4G, which combines a global adaptive schedule based on token-wise denoising difficulty with dynamic conditioning modulation using graph attention and conditioning sensitivity. It also introduces Factual Grounding (FGT) and Edit Sensitivity Rate (ESR) to evaluate reliable graph-to-sequence generation. Across WikiOFGraph, GenWiki, and TekGEN, conditioning-aware modulation improves grounding, edit sensitivity, and generation quality over difficulty-only adaptation.
Critical strengths
- The paper studies three complementary properties of reliable G2S generation: generation quality, factual grounding, and edit sensitivity.
- DLM4G combines a global adaptive schedule with dynamic conditioning modulation using graph attention and conditioning sensitivity.
- Across three benchmarks, conditioning-aware modulation improves grounding, edit sensitivity, and generation quality over difficulty-only adaptation.
Critical weaknesses
-
It is unclear why positions that depend more on the graph should receive less noise. Adding more noise might instead encourage the model to rely more on the graph. Comparing these two choices would help justify the design.
-
The ablations show that graph attention and conditioning sensitivity help, but do not show whether the global adaptive schedule is necessary. Could these conditioning signals achieve similar results on their own? An additional comparison would help answer this.
Questions for authors
see weakness. My current assessment is borderline. I would maintain a positive recommendation if the authors adequately address my concerns.
2 comments
Response to W2
W2: "The ablations show that graph attention and conditioning sensitivity help, but do not show whether the global adaptive schedule is necessary. Could these conditioning signals achieve similar results on their own? An additional comparison would help answer this."
We thank the reviewer for identifying this missing comparison. We agree that the original component ablations (Table 4) evaluate graph-conditioning signals alongside the global difficulty schedule, without isolating their independent effectiveness.
We therefore introduce a conditioning-only variant that removes the global difficulty-based schedule while retaining graph attention and conditioning sensitivity. In this variant, noise adaptation is determined by graph-conditioning signals without using token-wise reconstruction difficulty. This directly tests whether conditioning information alone can achieve performance comparable to the full framework.
| Variant (WikiOFGraph) | BLEU | [email protected] | ESR@1 | ESR@2 | Relation ESR |
|---|---|---|---|---|---|
| Base schedule | 0.60 | 0.77 | 0.64 | 0.53 | 0.52 |
| Difficulty only () | 0.62 | 0.79 | 0.65 | 0.54 | 0.53 |
| Conditioning only () | 0.63 | 0.79 | 0.66 | 0.57 | 0.54 |
| Full () | 0.65 | 0.83 | 0.68 | 0.60 | 0.58 |
The conditioning-only variant improves over the base schedule and performs comparably to or better than difficulty-only adaptation. However, neither component alone matches the full framework. Adding difficulty-aware adaptation to conditioning-only improves BLEU from 0.63 to 0.65, [email protected] from 0.79 to 0.83, ESR@2 from 0.57 to 0.60, and relation-edit ESR from 0.54 to 0.58.
Our conditioning-only ablation therefore provides empirical evidence that the global difficulty-based schedule contributes beyond graph conditioning alone, with the strongest performance achieved by combining both sources of information.
The new conditioning-only and inverse-noising ablations are preliminary single-run evaluations. We will include three-seed statistics, precise schedule configurations, and reproducibility details in the revised manuscript.
We sincerely thank the reviewer for their constructive feedback, which has helped strengthen the paper. We hope our responses and the new experiments address the concerns raised, and, if so, we would greatly appreciate it if the reviewer would consider increasing their score. We remain happy to address any further questions during the discussion period.
Response to W1
We thank the reviewer for the positive assessment and constructive questions. We address both concerns below with additional experiments.
W1: "It is unclear why positions that depend more on the graph should receive less noise. Adding more noise might instead encourage the model to rely more on the graph. Comparing these two choices would help justify the design."
We agree that stronger corruption may encourage greater reliance on graph conditioning. However, greater reliance does not necessarily ensure accurate factual reconstruction. Consider a graph containing
(Company C, founded_by, Person A),(Company C, led_by, Person B), and(Company C, founded_in, 2013), with the target sentence:“Company C was founded by Person A in 2013 and is led by Person B.”
Consider two illustrative intermediate recovery states (conceptual representations, not literal Gaussian-corrupted outputs):
In Case B, the denoiser must reconstruct not only the entities but also their correct associations with relation-bearing positions. An imperfect denoiser might generate:
“Company C was founded by Person B in 2013 and is led by Person A.”
Both entities are present in the graph and output, but their relationships are reversed. The problem is not missing graph information, but whether the denoiser can correctly retrieve and align that information under strong corruption. More noise may increase dependence on the graph while simultaneously removing information from the noisy sequence zt that helps determine which graph fact belongs at each output position.
Our attention analysis is consistent with this intuition (Figure 3a). On WikiOFGraph, graph-attention AUROC increases from 0.61 at high noise to 0.83 as denoising progresses, indicating that graph-supported positions are localized more reliably as the sequence representation is refined. This motivates retaining sufficient signal at difficult, graph-dependent positions. Difficulty-aware noise allocation is also supported by prior work (SeqDiffuSeq, Yuan et al., 2024; Meta-DiffuB, Chuang et al., 2024).
Inverse-noising ablation. To test the alternative, we trained an inverse-noising variant that reverses the adaptive schedule shift in Eq. 1 while retaining graph-conditioning modulation (Eq. 2), so positions receiving stronger adaptation undergo increased corruption.
The inverse-noising variant underperforms even the base schedule. Compared with DLM4G, factual grounding decreases from 0.83 to 0.62, ESR@2 from 0.60 to 0.41, and relation-edit ESR from 0.58 to 0.47. These results are consistent with more difficult factual and relational recovery under stronger corruption, as illustrated above.
Thus, stronger corruption at graph-dependent positions does not translate into better factual reconstruction in our setting. Instead, retaining additional signal at difficult, graph-dependent positions achieves substantially better grounding and edit sensitivity. We will clarify this motivation and incorporate the inverse-noising comparison into the revised manuscript.