- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper studies how to generate short driving suggestions together with reasons and localized visual evidence. The authors build CODA-GRD by reorganizing CODA-LM annotations and propose CEDAR based on Florence-2. The method combines grounding pretraining, a latent Reason–Evidence–Suggestion cascade, reason-aware contrastive learning, and branch-wise GRPO. Experiments on CODA-GRD and three additional driving datasets show improvements on the reported metrics over several baselines.
Critical strengths
- The task is practically useful. Separating the suggestion, reason, and object locations makes the output easier to inspect and provides a clear interface for studying driving recommendations.
- On CODA-GRD, the overall score improves from 26.25 to 29.82, with improvements also reported on LingoQA and DriveCoT. These results provide useful evidence that the combined design improves the model on the evaluated tasks.
Critical weaknesses
-
My main concern is that the evaluation does not directly validate the claimed evidence-grounded and concise recommendations. The text-overlap metrics, including ROUGE-L used as the training reward, do not directly assess whether the generated evidence and reasons support the suggested action. Table 8 evaluates annotation quality, while Figures 4–5 mainly show annotation examples involving construction vehicles and similar, direct suggestions. The paper does not provide comparative model outputs on cases requiring evidence selection among multiple objects or reasoning about spatial relations. It remains unclear whether the gains reflect these abilities or mainly common associations between object categories and suggestions. Quantitative evaluation of conciseness is also missing.
-
The method introduces several modules and training stages, but the benefit of some components remains unclear. Although the paper provides several ablations, the cumulative component study does not fully isolate their contribution in the final system. RCA improves Overall only from 28.22 to 28.24 in Table 4(a), while the Evidence average decreases from 73.43 to 72.42 after adding the pretraining tasks in Table 4(e). These results need further explanation and estimates of variation across runs. A simpler Florence-2 configuration using matched data and a comparable training budget, including GRPO, would also help determine whether the additional components are needed.
Questions for authors
-
Do you have results for a simpler Florence-2 baseline using the same training data and a comparable training budget, including GRPO?
-
Could you provide comparisons on cases requiring evidence selection among multiple objects or spatial reasoning, with human assessment of decision correctness and evidence support?
-
Could you clarify how Reason and Suggestion annotations are extracted, and how the external datasets are prepared and split?
-
Do the external results use models trained only on CODA-GRD or models fine-tuned on each target dataset?
5 comments
Response to Reviewer 11VS(2/2)
Q5: Component Contributions and Training Stages
(i) Independent ablations. To address your concern about the limited improvement from RCA (in Table 5(a)), we further evaluate Baseline+CCR,Baseline+RCA, Baseline+Pre, and Baseline+RL independently.
| Method | Evidence | Suggestion | Reason | Overall |
|---|---|---|---|---|
| Baseline | 72.64 | 20.44 | 13.51 | 26.25 |
| Baseline+CCR | 73.44 | 21.32 | 17.03 | 28.22 |
| Baseline+RCA | 72.97 | 20.89 | 17.16 | 28.01 |
| Baseline+Pre | 71.96 | 20.52 | 13.64 | 26.23 |
| Baseline+RL | 75.82 | 21.11 | 14.36 | 27.42 |
Although RCA provides only a modest additional gain when combined with CCR (28.22→28.24), applying RCA independently improves Overall from 26.25 to 28.01, particularly benefiting Reason (13.51→17.16). This shows that RCA contributes to reasoning performance, although its benefits may partially overlap with CCR. Meanwhile, RL independently improves Evidence from 72.64 to 75.82. Pretraining alone does not improve Overall (26.25→26.23), as its grounding-oriented objectives differ from the final generation objectives. This is expected, since pretraining is designed to provide grounding support rather than directly optimize downstream performance.
The results are included in Table 5(a)(Page 9) of the revised manuscript .
(ii) Contribution of Grounding Pretraining. We acknowledge the reviewer's observation that Evidence decreases from 73.43 to 72.42 after adding ECA and EPV (Pretraining in Table 5(e)). However, grounding pretraining is designed to strengthen entity-level visual grounding and support the joint learning of Evidence, Reason, and Suggestion, rather than optimize Evidence in isolation. With pretraining, Suggestion improves from 21.16 to 21.54, Reason from 17.24 to 18.33, and Overall from 28.24 to 28.68. These results suggest that pretraining contributes to a better balance across the three tasks, despite the modest decrease in Evidence performance.
To further examine its contribution under RL-based refinement, we compare CEDAR with variants that remove either the entire pretraining stage or EPV alone:
| Method | Evidence | Suggestion | Reason | Overall |
|---|---|---|---|---|
| CEDAR w/o pre | 74.47 | 22.58 | 18.66 | 29.59 |
| CEDAR w/o EPV | 76.19 | 22.07 | 18.66 | 29.67 |
| CEDAR | 75.75 | 22.61 | 18.67 | 29.82 |
Removing the entire pretraining stage reduces Evidence from 75.75 to 74.47 and Overall from 29.82 to 29.59, further supporting the contribution of grounding pretraining to the complete framework. Removing EPV alone, in contrast, increases Evidence to 76.19 but decreases Suggestion from 22.61 to 22.07 and Overall from 29.82 to 29.67. This indicates that EPV introduces a trade-off in Evidence performance while contributing to better Suggestion generation and overall performance. Taken together, these results suggest that grounding pretraining contributes to a better balance across the three tasks, despite the modest decrease in Evidence.
These results are reported in Table 5(a) (Page 9), and Table 10 (Page 16) of the revised manuscript.
(iii) Comparable training budget. To further address your concern about whether the improvements come mainly from additional training stages, we evaluate a simpler Florence-2 configuration incorporating Pretraining and GRPO, without CCR and RCA. The comparison is presented below:
| Method | Evidence | Suggestion | Reason | Overall |
|---|---|---|---|---|
| Baseline + Pre + GRPO | 70.56 | 21.16 | 14.06 | 26.44 |
| CEDAR | 75.75 | 22.61 | 18.67 | 29.82 |
Although the simpler configuration also includes Pretraining and GRPO, its Overall score reaches 26.44, compared with 29.82 for CEDAR. CEDAR achieves higher performance across Evidence, Suggestion, and Reason.
The results are included in Table 11 of the revised manuscript (Page 16).
Q6: External Benchmark Training Protocol
The external results use dataset-specific fine-tuning, rather than zero-shot evaluation of a CODA-GRD-only model. CEDAR and comparison models are fine-tuned on the respective target datasets and evaluated on their test sets.
Compared with the task-specific Florence-2 Baseline, CEDAR improves Overall from 46.93 to 51.21 on LingoQA, 40.36 to 43.38 on DriveCoT, and 21.90 to 22.56 on OmniDrive (Tables 2 and 4 and Appendix Table 7).
Dear Reviewer 11VS, thank you sincerely for the time and effort in reviewing. As the discussion deadline approaches in just under two days, we would like to kindly ask whether you have any additional questions or if there are any further experiments you would like us to consider. We are truly happy to provide additional theoretical analysis or experimental results as soon as possible to help clarify any points of concern. Your feedback is truly valuable to our work, and we would be grateful if we could receive your recognition.
Response to Reviewer 11VS(1/2)
We thank the reviewer for recognizing the practical value of separating driving suggestions, reasoning, and object locations, as well as the consistent improvements on CODA-GRD, LingoQA, and DriveCoT. We address the concerns as follows:
Cross-component evaluation. We agree that text-overlap metrics alone cannot establish whether Evidence and Reason support Suggestion. Following your comments, we therefore add CLIP-based Evidence–Reason (E–R) and Reason–Suggestion (R–S) similarity, together with human assessment of Evidence–Suggestion (E–S) support on 200 samples:
Compared with the Baseline, CEDAR improves E–R from 0.227 to 0.242, R–S from 0.76 to 0.81, and E–S human agreement from 68.5% to 75.0%. These improvements provide complementary evidence of stronger cross-component consistency, while CEDAR remains competitive with external models.
These evaluation results have been added to Table 3 and Sec. 4.1 (Page 8, Lines 414–424) of the revised manuscript.
Following your comments, we have added four qualitative examples covering simple and complex scenes with multiple traffic entities, including pedestrians, construction vehicles, barriers, and surrounding cars (Appendix 6.4, Fig. 5 (Page 17)). Unlike Figs. 6–7, these examples present model-generated Evidence, Reason, and Suggestion, illustrating their relationships in different driving scenarios.
The original CODA-LM
driving_suggestionaverages 91.65 words, and OmniDriveactionaverages 89.70 words, whereas CODA-GRD Suggestion averages 20.16 words. Moreover, CEDAR-generated Suggestions average 20.84 words. Our objective is to make driving actions explicit and concise while preserving supporting explanations separately in Reason and Evidence.The length comparison has been added in Sec. 4.1 (Page 7, Lines 376-377) .
(i) Annotation extraction. We adopt rule-guided text decomposition using causal discourse cues and contextual information to separate action-oriented Suggestions and explanatory Reasons from original CODA-LM driving suggestions, followed by manual screening and refinement.
(ii) External datasets. We clarify the preparation and splits in Appendix 6.1(External Datasets, Page 14, Lines 702–710):
External benchmarks evaluate Suggestion and Reason without structured Evidence supervision.