- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes question-guided self-distillation (a form of OPSD) for reducing false-positive hallucinations in VLMs. A frozen teacher receives verification subquestions as privilige knowledge, while the student learns to answer directly through on-policy distribution matching and a reference objective. Results show improvements on FINER wh questions and general benchmarks.
Critical strengths
- The paper addresses an important reliability issue and explicitly examines both false-premise correction and valid-answer retention.
- The method requires no additional verification at deployment. The teacher-context ablation supports the usefulness of question-specific guidance.
- Experiments on two model backbones show consistent wh improvements, while pair-level analyses help explain the corrections and regressions.
Critical weaknesses
-
Antidote [1] is relevant prior work on counterfactual presuppositions and factual-prior-guided self-correction by preference optimization, but is not discussed. The paper should clarify how its answer-free, question-derived guidance differs from factual-prior guidance and what additional contribution it offers.
-
The methodological novelty appears incremental: the approach combines OPD, question-derived teacher context, and reference regularization. The current ablation does not isolate the contributions of on-policy sampling and the reference term, leaving the benefit beyond teacher prompting unclear.
-
Improvements are concentrated on wh questions. Table 1 shows regressions on several object and relation settings across both backbones. On DOCCI wh, positive-query accuracy also drops from 83.60% to 80.63%, indicating unresolved over-rejection.
-
Table 3 uses different evaluation processing across methods. Appendix B reports answer normalization and additional V* visual verification for the proposed model, while Base and DPO retain direct results.
[1] Wu et al., “Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object Perception,” CVPR 2025.
Questions for authors
- A discussion of Antidote and evaluation on CP-Bench would help clarify the contribution and generalization. Comparing question-derived guidance with factual-prior guidance would further strengthen this analysis.
- Ablations on on-policy sampling and reference regularization, together with stronger teacher-prompt controls, would help establish the contribution of each component.
- Further analysis of the non-wh regressions and increased rejection rate of valid questions would help clarify the method’s benefits and limitations.
7 comments
| Model | Obj | Attr | Rel | WH | WH Correct-Premise Acc. | WH Incorrect-Premise Acc. |
|---|---|---|---|---|---|---|
Base | 74.38 | 73.82 | 64.25 | 47.13 | 85.91 | 57.93 |
Guidance-only | 73.71 | 77.11 | 67.01 | 58.94 | 77.45 | 79.60 |
Reference-only | 74.22 | 73.82 | 64.49 | 48.01 | 86.48 | 58.31 |
Full OPD (Ours) | 75.11 | 77.23 | 66.17 | 58.12 | 83.13 | 72.96 |
The guidance loss provides the main corrective gains: compared with Base, WH paired accuracy improves by +11.81%, while accuracy on WH questions with correct premises decreases by 8.46%. This indicates that strengthening correction alone can reduce the ability to answer valid questions.
The reference loss complements the guidance loss: it preserves gains over the base model on Attr, Rel, and WH while improving Obj accuracy over Guidance-only to 75.11%, exceeding Reference-only and the baseline. This suggests that the reference term constrains capability shifts during correction, helping balance corrective gains with capability preservation.
3. Teacher-prompt Controls
Differences across question types: To analyze the effects of different teacher prompts on performance, we evaluate the same frozen Qwen3-VL-8B baseline on CompreCap and DOCCI under identical evaluation conditions, comparing three input settings: the original direct input , a generic verification reminder, and question-specific verification subquestions . Paired accuracy for each question type is reported below.
| Dataset | Type | Direct(Qwen v3) | Generic | Specific | S−D (pp) | S−G (pp) |
|---|---|---|---|---|---|---|
CompreCap | Obj | 74.73 | 76.16 | 74.67 | −0.06 | −1.49 |
CompreCap | Attr | 73.34 | 75.13 | 76.69 | +3.36 | +1.56 |
CompreCap | Rel | 64.11 | 67.66 | 65.47 | +1.36 | −2.20 |
CompreCap | WH | 47.25 | 58.50 | 70.44 | +23.18 | +11.94 |
DOCCI | Obj | 59.26 | 59.68 | 59.78 | +0.52 | +0.10 |
DOCCI | Attr | 62.58 | 64.77 | 66.47 | +3.88 | +1.70 |
DOCCI | Rel | 53.63 | 55.59 | 54.84 | +1.21 | −0.75 |
DOCCI | WH | 37.73 | 47.73 | 59.09 | +21.36 | +11.36 |
The benefits of different teacher prompts vary across question types. Generic improves all question types on both datasets over Direct, while Specific further improves WH performance. These results indicate that generic reminders provide broader verification benefits, whereas question-specific subquestions primarily benefit WH premise verification, consistent with our goal of improving WH performance on FINER.
Weakness 3 & Question 3: Further analysis of the non-wh regressions and increased rejection rate of valid questions would help clarify the method’s benefits and limitations.
Thank you for your suggestion. This pattern is consistent with our design rationale. Motivated by FINER's limited ability to mitigate false-positive hallucinations in WH questions, we developed OPD building on FINER's study of false-positive hallucinations, aiming to improve its weaker false-premise handling in WH questions while preserving performance on other question types as much as possible.
To this end, we combine the guidance loss with on-policy sampling. Compared with FINER-DPO, this yields clear improvements in WH paired accuracy across both datasets and both backbones. For Qwen3-VL-8B, the gains on the two datasets reach 11.37% and 10.59%, respectively. The non-WH regressions are smaller than the WH gains, resulting in better overall performance.
To mitigate the increased rejection of valid questions induced by the guidance loss, we introduce a reference loss anchored to the frozen base model. Compared with using the guidance loss alone, this raises WH positive-query accuracy from 77.45% to 83.13%.
Other Weaknesses:
Regarding the concern that the benefit may be limited to teacher prompting, we clarify that the full method not only improves teacher prompting but also transfers the guidance along the student's actual response trajectories and removes the additional guidance context at deployment. The additional on-policy sampling ablation supports this contribution. We will include the non-WH regressions and over-rejection of valid questions in the Limitations section of the revised paper. Regarding evaluation processing, we clarify that no additional verification was used; only response formatting was standardized for a fairer comparison.
Dear Reviewer F5qT,
We sincerely appreciate your time and effort in providing such thoughtful reviews and insightful comments.
Could you please kindly let us know if our rebuttal has addressed your concerns?
If you have any further questions regarding our work, we would be delighted to address them.
If our responses have addressed your concerns, we would greatly appreciate your reconsideration of your overall assessment.
Best regards,
Authors
Thank you for pointing out Antidote. We trained OPD on LLaVA-1.5-7B, matching the baseline used in the original Antidote work, and conducted additional experiments using GPT-4o as the judge and following the CP-Bench V2 evaluation procedure publicly released by the Antidote authors.
1. Gains and Trade-offs on CP-Bench V2
BaseOursAntidoteThe original Antidote paper reports results on CP-Bench V1, whereas the version currently released by the authors is V2. Our model use a publicly available mirror of the CP-Bench dataset and follow the V2 evaluation procedure. To facilitate interpretation, we mathematically convert V1 metrics reported in the original Antidote paper (the Base and Antidote results) into the same metric format used in V2. Antidote’s official public resources do not include the complete training dataset or the trained model weights; therefore, we did not independently reproduce its training.
OPD improves false-premise rejection. Our model achieves a substantially higher CPQ rejection rate than the other models, consistent with our goal of reducing false-positive hallucinations in VLMs.
OPD still exhibits reduced true-premise acceptance. Suppressing hallucinations induced by false premises leads OPD to adopt a more conservative response tendency, while Antidote performs better at accepting true-premise questions.
2. Differences from Factual-prior Guidance
Antidote: Uses facts such as object presence or absence in synthetic data to guide self-correction, then constructs preference pairs for DPO. It also incorporates true-premise questions to mitigate excessive caution.
Ours: Provides only conditions to verify, without verification answers. The student matches the teacher's distribution along its own response prefixes, without requiring preconstructed preferred and dispreferred response pairs.
Thank you for your suggestion. We separately examine the contributions of on-policy sampling and reference regularization and introduce additional teacher-prompt controls.
1. Contribution of On-policy Sampling. Using Qwen3-VL-8B-Instruct as the baseline, we compare the paper's on-policy sampling approach with a variant that uses fixed samples from the initial student.
OPDFixed Initial PrefixesMetric: CompreCap paired accuracy (%, higher is better); the macro average weights the four question types equally.
The variant uses fixed prefixes generated in advance by the initial student, while student parameters continue to update. Both settings use the same question-specific verification context, loss function, and training budget.
On-policy sampling improves performance across all four question types, supporting its contribution in this setting: as the student policy evolves, distillation along its current response trajectories is more effective than reusing fixed prefixes from the initial policy.
2. Individual Contributions of the Guidance Loss and Reference Loss
We evaluate four models on the CompreCap dataset. The table below reports paired accuracy for Obj, Attr, Rel, and WH, along with accuracy on WH questions with correct and incorrect premises.