- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper studies reliability in diffusion vision-language models (VLMs). The authors show that on dynamically decoded LLaDA-family diffusion VLMs, final output confidence fails to detect the model’s own errors: AUROC is only 0.50 on POPE (chance) and 0.37–0.39 on GQA (below chance). They attribute this to the sampler committing high-confidence positions during denoising, which sharpens the final distribution and erases the model’s internal doubt. As an alternative, they read the per-step entropy at the answer position along the denoising trajectory and average it (mean step entropy), yielding a training-free, single-pass error-detection signal. This signal reaches 0.65–0.79 AUROC across four diffusion VLMs. They further build SEISMO: a logistic calibration head reduces ECE by 2.7×, and a Learn-then-Test gate provides a distribution-free hallucination-risk guarantee. Experiments cover POPE, GQA, MME, HallusionBench, AMBER, and medical VQA, with boundary analyses for open-ended generation, the medical domain, and non-LLaDA backbones. They also show the signal can diagnose but not repair errors, though it can route suspicious questions to an AR fallback.
Critical strengths
-
An important and counterintuitive finding: output confidence in diffusion VLMs can be anti-calibrated. This directly challenges reliability methods transferred from AR models. It has broad implications for the multimodal reliability and uncertainty-quantification communities, because it shows that a reliability method can silently invert under a new generation paradigm rather than merely degrade.
-
A training-free, single-pass trajectory signal: mean step entropy is read directly from the model’s existing decode, adds no compute, and is stable across multiple models and benchmarks. Combined with a calibration head and Learn-then-Test risk control, it provides a full pipeline from detection to guarantees. This is the first distribution-free hallucination-risk guarantee for diffusion VLMs and has practical deployment potential.
Critical weaknesses
Generality is limited to LLaDA-family models and short-answer QA: the advantage appears only on dynamically decoded LLaDA-initialized models; forcing the Dream backbone into dynamic decoding did not transfer the signal. The signal also fails in open-ended generation. This makes the method more of a diagnostic tool for a specific model family than a general solution for diffusion VLMs. Given the claim of a reliability framework for diffusion VLMs, the scope is narrow.
Questions for authors
-
Have you tried replacing “mean step entropy” with “mean step max probability”? Both can separate correct from incorrect answers in early steps, but entropy is stronger. Can you provide this ablation to show which part of the distribution shape drives entropy’s advantage?
-
In open-ended generation, mean step entropy is highly correlated with commit step (rank corr. 0.84). After residualizing on commit step, do any other trajectory statistics retain signal? Have you tried grouping mentions by commit stage?
-
For non-LLaDA backbones such as Dream, the advantage did not transfer even under forced dynamic decoding. Have you analyzed how Dream’s early-step entropy distribution differs fundamentally from LLaDA’s? Does this imply the trajectory signal depends on a specific representational structure?
-
SEISMO-Guard requires a labeled calibration set. In deployment scenarios where same-distribution labeled data are unavailable, have you considered unsupervised or weakly supervised ways to estimate the calibration threshold? The conservative transfer property fails under upward drift; can the sequential e-process monitor provide early warning rather than only post-hoc alarms?
5 comments
Response to Reviewer kLn1 (2/2)
Q2. "In open-ended generation, mean step entropy is highly correlated with commit step (rank corr. 0.84). After residualizing on commit step, do any other trajectory statistics retain signal? Have you tried grouping mentions by commit stage?"
The paper already measures this link and already removes the commit step from our score (Section 6 on page 9 and Appendix G on page 34). Now we also did this for the other step signals and grouped the mentions by stage as you asked. After removing the commit step the signal read after the answer settles still finds wrong objects at 0.61 to 0.62. This is the same level as confidence (0.60 to 0.61). So the path carries real content and not only decoding order.
| Commit stage | Early | Middle | Late |
|---|---|---|---|
| Path signal after the answer settles | 0.57 | 0.56 | 0.68 |
| SEISMO score (all steps) | 0.48 | 0.53 | 0.65 |
The signal is strongest for objects placed late. SEISMO also maps where path based detection helps most and explains why. In short answer questions the answer is contested and SEISMO leads by a lot. In long free captions the score partly becomes a decoding order clock. So there it matches confidence instead of beating it (Section 6).
Q3. "For non-LLaDA backbones such as Dream, the advantage did not transfer even under forced dynamic decoding. Have you analyzed how Dream’s early-step entropy distribution differs fundamentally from LLaDA’s? Does this imply the trajectory signal depends on a specific representational structure?"
The paper already points to the answer in Section 6 (page 8). The gain appears where decoding squeezes the early doubt out of the final answer. Here we show this directly with the shape of the doubt curve. The table shows the median answer entropy on POPE.
| Model | Doubt at step 1 | Doubt at the last step | How much it shrinks |
|---|---|---|---|
| LLaDA-V | 2.11 | 0.003 | about 830 times |
| LaViDa-Dream | 0.11 | 0.10 | 1.1 times |
| Dream-VL | 0.70 | 0.30 | 2.4 times |
| Dimple | 0.27 | 0.21 | 1.3 times |
LLaDA-V starts very unsure. Decoding then squeezes the doubt out of the final answer. Only the path keeps it. Dream based models start with far less doubt and lose much less of it by the last step. So their final confidence still holds the doubt and works well (0.78 to 0.82). It is not about a special inner structure. When Dream models answer late (GQA) SEISMO wins on them too. This is a direct test of how SEISMO works. The gain shows up exactly where decoding squeezes out early doubt.
Q4. "SEISMO-Guard requires a labeled calibration set. In deployment scenarios where same-distribution labeled data are unavailable, have you considered unsupervised or weakly supervised ways to estimate the calibration threshold? The conservative transfer property fails under upward drift; can the sequential e-process monitor provide early warning rather than only post-hoc alarms?"
- Setting the threshold. Every error guarantee needs some labels. Only a label can tell us that an answer is wrong. SEISMO needs just one labeled set at the start. Appendix C.5 (page 29) already shows that the same threshold then stays safe on easier data with no new labels.
- Early warning without labels. Yes. The paper already has a monitor that uses labels (Table 12 on page 29). We have now added a second monitor that needs no labels at all. It simply counts how often SEISMO holds back an answer. If SEISMO starts holding back more answers than it did on POPE then the questions have become harder and the monitor raises an alarm. We set it up on POPE. Then we ran it on the other POPE splits and on four harder benchmarks.
| Used on | Is the guarantee still safe? | How often the new monitor raised an alarm | Questions before the alarm (median) |
|---|---|---|---|
| POPE random and popular and adversarial | yes | 1% or less | not needed |
| HallusionBench | no | 100% | 36 |
| AMBER | no | 100% | 58 |
| MME | no | 100% | 211 |
| GQA | no | 100% | 5 |
The new monitor raised an alarm every time the guarantee broke. It did this without a single label. When nothing changed it gave a false alarm only 2.6% of the time. The labeled monitor caught HallusionBench and AMBER only 6% and 25% of the time. On these two the error is only a little above the limit so labels give a weak signal. The number of held back answers changes much more and the new monitor catches it every time.
With this SEISMO covers every stage of use. It sets a safe threshold at the start. It warns early without labels. It also double checks once labels arrive.
Thank you for the authors’ additional clarifications. The research direction is potentially meaningful, but the manuscript’s writing and argumentative structure remain insufficiently clear. The connections among the motivation, methodology, and main contributions are not always well articulated, which makes the central message difficult to follow.
Response to Reviewer kLn1 (1/2)
Thank you for the positive review and the sharp questions. Each one gave us new results. Together they make SEISMO broader than the paper first claimed.
Main concern. "Generality is limited to LLaDA-family models and short-answer QA: the advantage appears only on dynamically decoded LLaDA-initialized models; forcing the Dream backbone into dynamic decoding did not transfer the signal. The signal also fails in open-ended generation. This makes the method more of a diagnostic tool for a specific model family than a general solution for diffusion VLMs. Given the claim of a reliability framework for diffusion VLMs, the scope is narrow."
The paper already maps where the step signal helps and where it does not (Section 5.3 on page 6 and the Limitations on page 9). We have now gone further. SEISMO is not limited to LLaDA models. We tested three model families. SEISMO beats the model's own confidence in 5 of 9 tests. It ties in the other 4. It never loses.
This turns a limit into one of SEISMO's strongest results. One simple rule holds across three families. If the answer is read after the model has written its own text then confidence fails and SEISMO recovers the signal. This happens with long answers (LLaDA-V and Nemotron). It also happens on hard questions where the answer is placed late (every GQA test). We read every Dream model through its own built in hook. Our earlier LaViDa-Dream capture read the answer one position too late. These new numbers replace those results and the forced Dream test in Appendix B.10. The POPE conclusion does not change.
Q1. "Have you tried replacing “mean step entropy” with “mean step max probability”? Both can separate correct from incorrect answers in early steps, but entropy is stronger. Can you provide this ablation to show which part of the distribution shape drives entropy’s advantage?"
Section 3.2 (page 4) already uses both final max probability and final entropy as baselines. Here is the full ablation over all steps that you asked for.
What matters is reading the whole decoding path. That is the SEISMO idea. Both path based scores beat final confidence by about 0.3. On yes or no questions the two scores are almost the same (rank correlation 0.97). On open GQA questions entropy is a bit better. It also sees how the chance is spread over other possible answers. That part alone scores 0.75. This is why SEISMO uses entropy.