- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper identifies a shortcut problem in Vision-OPD, where models can predict correct answers without relying on relevant visual evidence. To address this, the authors propose CV-OPD, which uses contrastive supervision and discrepancy-based gating to encourage better visual grounding.
Critical strengths
- Clear motivation. The paper identifies an important limitation of existing Vision-OPD methods and supports it with experiments on masked visual regions.
- Intuitive and well-structured method. The proposed CDL and DAG provide a straightforward way to introduce contrastive visual supervision into OPD. The overall framework is easy to follow and builds naturally on the existing Vision-OPD approach.
Critical weaknesses
-
The evidence for improved visual grounding is not fully convincing. In Sec. 2.2, the base model already achieves around 42% accuracy when the answer-relevant evidence is masked, suggesting that visual shortcuts may already exist before OPD. The paper does not sufficiently explain why models can still produce correct answers without the necessary visual evidence, or whether the proposed method truly addresses the underlying issue. More controlled experiments and a deeper analysis of this behavior would strengthen the central claim.
-
Limited improvement over strong baselines and unclear sources of performance gains. Although CV-OPD improves over Vision-OPD, its performance is very close to VAD (78.22% vs. 78.11%). It remains unclear whether this small improvement is meaningful and whether the gains from CDL and DAG come from better visual grounding rather than additional regularization or sample filtering. More targeted ablations and controlled comparisons would help establish the effectiveness of the proposed components.
Questions for authors
- Could the authors provide a more direct evaluation, such as comparing the effects of masking answer-relevant and irrelevant regions?
- How is the attention in Fig. 2(b) calculated? Is it averaged across the entire response sequence, or computed using specific tokens, layers, or attention heads?
- How sensitive is the method to incorrect positive crops or negative crops that still contain relevant evidence?
- The quality of Fig. 1(b) is difficult to read due to its low resolution.
- Why does Vision-OPD still achieve relatively high, even higher accuracy when the answer-relevant visual evidence is masked? A deeper analysis of why this happens would strengthen the paper's motivation and central claim.
- Can the authors demonstrate that the improvements from CDL and DAG come from better visual grounding rather than additional regularization or sample filtering?
Reminder of Discussion
Dear sG4v,
Thank you for your time and effort. We were wondering whether our responses have addressed your concerns and whether you have any further questions. Please feel free to share any remaining concerns and we would be happy to discuss how we can further improve this work.
Best regards,
Authors