- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies two sources of unreliable LVLM responses: a question may contain required premises that conflict with the image, and the model's answer may introduce content unsupported by visual evidence. The authors propose PAVER, a training-free framework that separately parses required premises from the question and inspection targets exposed by an initial draft. The former determine whether the question remains answerable, whereas the latter only guide Grounding DINO and Florence-2 in acquiring visual evidence. A premise-aware router then chooses between refusal and evidence-grounded re-answering. Experiments with LLaVA-1.5-7B and Qwen3-VL-8B on six benchmarks report improvements in open-ended hallucination, object-existence judgments, false-premise recognition, and selective answering. Pathway ablations, response-length controls, and intermediate-representation audits are used to support the claimed division of labor: premise modeling handles question validity, while draft-guided inspection improves answer-side reliability.
Critical strengths
-
The paper does not treat every visual conflict as grounds for refusal, which directly avoids the flawed policy of refusing whenever a mentioned entity is not detected.
-
The evaluation covers both answer-side and premise-side reliability. The six benchmarks span open-ended generation, object existence, counting, position, color, false premises, and insufficient context.
-
The ablations and representation audits are well targeted.
Critical weaknesses
-
The main comparison changes both inference compute and available evidence, so it is not fair. PAVER includes draft generation, two parsing stages, Grounding DINO, Florence-2, routing, and final generation. Consequently, part of the improvement may come from additional visual models and multi-stage computation rather than premise/query role modeling itself.
-
The selected operating point entails substantial over-refusal and information-loss trade-offs that are not summarized under a common utility.
-
The premise-side evidence depends heavily on one automatic judge, while the human validation is small and lacks agreement statistics.
Questions for authors
-
With the draft, Grounding DINO/Florence-2 outputs, number of LVLM calls, and token budget held fixed, how does a role-agnostic baseline perform if all evidence is given to a single answering prompt?
-
Does the router expose a tunable threshold or confidence signal that would allow the authors to report curves over refusal rate, false-refusal rate, incorrect-answer rate, and answer coverage?
5 comments
Response to Reviewer kmDh (Part 2)
3. Quantifying refusal trade-offs and information retention
The selected operating point entails substantial over-refusal and information-loss trade-offs that are not summarized under a common utility.
To quantify the trade-off between correctly rejecting false-premise questions and incorrectly rejecting valid questions, we introduce a cost-sensitive decision utility. We evaluate this utility on all 6,540 JBA examples using the benchmark judge's per-example classifications of the final responses. With false-premise questions as the positive class, and count correctly identified and missed false premises, respectively; and count valid-premise questions correctly accepted and incorrectly classified as false-premise, respectively. We define decision-level utility as
Each correct premise decision receives . The penalties and apply to false-positive and false-negative premise classifications, respectively. We fix and vary to evaluate the same final-response predictions under different error costs. The false-positive rate, , is the proportion of valid-premise questions classified as false-premise.
Table R4. Cost-sensitive decision utility on JBA (LLaVA-1.5-7B). Utility values are multiplied by 100.
| Method | False-premise recall | False-positive rate | ||||
|---|---|---|---|---|---|---|
| Vanilla | 22.29% | 1.59% | 21.19 | 20.80 | 20.40 | 20.00 |
| SHIELD | 30.19% | 4.92% | 26.58 | 25.35 | 24.12 | 22.89 |
| PAVER | 72.50% | 36.74% | 44.95 | 35.75 | 26.55 | 17.35 |
PAVER achieves the highest decision utility under equal error costs, outperforming SHIELD by 10.40 points and Vanilla by 14.95 points. Beyond this equal-cost setting, PAVER maintains the highest utility for false-positive penalties below approximately (with ), highlighting the trade-off between higher false-premise recall and additional false positives.
For information retention, at comparable response lengths, PAVER achieves lower hallucination rates and higher object coverage than length-matched Vanilla and MARINE on AMBER (Table 3), demonstrating a better hallucination–coverage trade-off.
Table R5. Hallucination and object coverage at comparable mean response lengths (AMBER Generation, Qwen3-VL-8B).
| Method | Mean length (words) | CHAIR | Cover | Hal | Cog |
|---|---|---|---|---|---|
| Vanilla (regenerated) | 59.8 | 5.6 | 60.7 | 25.7 | 1.0 |
| MARINE (regenerated) | 60.0 | 5.9 | 62.6 | 28.1 | 1.9 |
| PAVER (native) | 61.0 | 3.8 | 63.4 | 20.1 | 1.0 |
4. Expanded validation of premise extraction
The premise-side evidence depends heavily on one automatic judge, while the human validation is small and lacks agreement statistics.
We added a full-split premise-extraction audit using GPT-6.1 Sol as an additional evaluator. It assessed all 6,540 LLaVA JBA premise sets, complementing the original condition-blind human audit of 100 stratified questions. The criterion is strict: a premise set is correct only if it includes every required premise and contains no unnecessary or incorrect premise. Omissions, unsupported additions, semantic distortions, and leakage of queried content into the premise set are all counted as errors.
As shown in Table R6, GPT-6.1 Sol judges 86.36% of the premise sets extracted by PAVER's frozen LVLM backbone to be correct across all 6,540 JBA examples. This result is similar to the 83% Fully Correct rate obtained in our previous human validation (Table 9), providing further evidence of the reliability of LVLM-based premise extraction in PAVER.
Table R6. Full-split premise-extraction accuracy on JBA (LLaVA-1.5-7B), evaluated by GPT-6.1 Sol.
| Total | Correct | Incorrect | Accuracy ↑ |
|---|---|---|---|
| 6,540 | 5,648 | 892 | 86.36% |
Response to Reviewer kmDh (Part 3)
5. Confidence thresholds
Does the router expose a tunable threshold or confidence signal that would allow the authors to report curves over refusal rate, false-refusal rate, incorrect-answer rate, and answer coverage?
The current router outputs a discrete ANSWER/REFUSE decision and does not expose a tunable confidence threshold. It selects REFUSE when visual evidence contradicts a required premise and ANSWER otherwise.
In our early experiments, we tried prompting the model to output confidence scores and using an explicit threshold to determine whether to refuse. However, we found that the model tended to be overconfident, leading to poor performance. This observation is consistent with prior work on confidence elicitation in LLMs [2] and LVLMs [3] [4]. These studies distinguish verbalized confidence from more informative probability- or consistency-based measures, which would require a separate calibration design and validation. We therefore retain a discrete premise-aware router and the present experiments evaluate the effectiveness of this routing policy.
Taken together, we hope these additional results and clarifications adequately address your concerns. If so, we would greatly appreciate it if you could reconsider your assessment and rating.
References
[1] Yin, Shukang, et al. "Woodpecker: Hallucination correction for multimodal large language models." Science China Information Sciences 67.12 (2024): 220105.
[2] Xiong, Miao, et al. "Can llms express their uncertainty? an empirical evaluation of confidence elicitation in llms." International Conference on Learning Representations. Vol. 2024.
[3] Ding, Zhikai, Shiyu Ni, and Keping Bi. "Do LVLMs Know What They Know? A Systematic Study of Knowledge Boundary Perception in LVLMs." EMNLP (Findings). 2025.
[4] Groot, Tobias, and Matias Valdenegro-Toro. "Overconfidence is key: Verbalized uncertainty evaluation in large language and vision-language models." Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024). 2024.
Response to Reviewer kmDh (Part 1)
Response to Reviewer kmDh
We thank you for recognizing the importance of distinguishing required premises from queried content, the breadth of our evaluation, and the targeted ablations. To address the remaining concerns, we have added a routing ablation with matched evidence and inference budgets, a comparison with Woodpecker[1], a cost-sensitive JBA analysis, and a full-split audit of premise extraction.
1. Premise-aware routing improves reliability under matched evidence and inference budgets
PAVER uses separate LVLM calls for routing and generation, so merging them into a single answering prompt removes one call when the rest of the pipeline is unchanged. We therefore use two complementary controls: Full w/o Router tests the single-prompt design, and Generic Router tests the routing instruction with the call count and token budgets fixed.
A single answering prompt lowers MME-Hall from 658.3 to 415.3 (Table 8). Full w/o Router keeps the draft, extracted premises, grounding targets, and Grounding DINO and Florence-2 outputs fixed. It gives all visual evidence to one prompt that decides whether to answer and generates the final response.
With the same LVLM calls, token budgets, and visual evidence, Full PAVER outperforms Generic Router by 182.59 points on MME-Hall and 26.67 points on HaloQuest Overall (Table R1). Generic Router retains the explicit premises and the same final generation procedure. Only the routing instruction changes: it asks the model to refuse invalid questions and answer otherwise, without explicitly distinguishing required premises from queried content.
Table R1. Routing ablation with matched visual evidence and inference budgets (LLaVA-1.5-7B).
Generic Router refuses 42 of the 60 MME-Hall existence questions, while Full PAVER routes all 60 to ANSWER. These questions illustrate why the distinction matters: when a question asks whether an object is present, its absence supports the answer No.
Together, these complementary ablations demonstrate the benefits of premise-aware routing instructions and separating routing from response generation, beyond the effects of additional visual evidence and inference computation.
2. Comparison with multi-stage verification and correction methods
We reproduced Woodpecker using its released implementation. Woodpecker extracts concepts from a draft, formulates verification questions, checks visual evidence with external tools, and corrects the answer, making it a relevant comparison for the concern about additional tools and inference stages.
Table R2. Comparison with Woodpecker on LLaVA-1.5-7B.
Table R3. Efficiency comparison on the first 50 AMBER Generation examples.
PAVER outperforms Woodpecker across all reported benchmark metrics (Table R2), while achieving lower end-to-end latency and peak GPU memory usage (Table R3). These results demonstrate PAVER's advantages in both effectiveness and efficiency over this multi-stage verification-and-correction framework.