- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes Cross-sensor Rationale Projection (CRP) to address the challenge of directly transferring inference processes generated by privileged sensors to information-constrained deployment sensors. Specifically, CRP first generates an inference chain using information-rich sensors, then transforms it into inference content supported by the target sensor through four operations: Keep, Abstract, Hedge, and Remove. Consistency filtering is then used to construct training supervision for the student model. Furthermore, the authors propose Estimated Projection Value (EPV) to predict the potential gains of cross-sensor inference projection. Experiments are conducted on RadarQA-300 and AudioQA-300 benchmarks. Results show that CRP outperforms answer-only supervision and surpasses direct distillation methods across multiple models and fine-tuning settings.
Critical strengths
- This paper points out the differences in information observability in cross-sensor CoT distillation and proposes a solution to the problem of unreliable supervision that may be introduced by direct transfer privileged inference.
- Experiments cover different sensor scenarios.
Critical weaknesses
- The four inference projection operations lack fine-grained ablation. The paper does not adequately validate the independent contributions of Keep, Abstract, Hedge, and Remove, nor the necessity of using them in combination.
- The implementation details of the core projection process are insufficient.
- Potential confounding factors remain in the comparison with baseline methods. Although the student model training configuration is consistent, it is unclear whether the number of teacher calls, inference length, selection strategies, and number of effective training samples are consistent across different supervision methods.
- There is a lack of direct quantitative evaluation of the consistency of inference evidence. The experiments primarily focus on the accuracy of the final answer and have not yet sufficiently demonstrated that Projected-CoT actually reduces inference statements that the target sensor cannot support.
- The experimental scale is limited, and the computational cost and scalability of the method in practical deployment are unclear.
Questions for authors
- Is it recommended to ablate the Keep, Abstract, Hedge, and Remove operations to verify their individual contributions and the necessity of their combined use?
- Provide more experimental details. Include teacher model configuration, projection decision strategy, and a complete Prompt, and clarify whether the same teacher model is used in each phase.
- It is recommended to re-compare CRP with the existing baseline under conditions of matched teacher call budget, CoT length, screening strategy, and training sample size.
- Quantitatively analyze inference reliability. Quantitatively compare the quality of CoTs generated by different supervision methods.
- More detailed computational efficiency should be reported.
5 comments
I appreciate the authors' detailed response and supplementary experiments, which have clarified some of the questions. However, the existing experiments still do not adequately eliminate potential confounding factors in baseline comparisons, and the verification of the reliability of the inference is relatively limited. At the same time, the independent methodological contributions of the overall framework are not clearly defined. The method mainly combines teacher inference generation, text rewriting under target modality constraints, and supervised fine-tuning. Based on the above issues and other reviewers' concerns, I will maintain the original score.
Round 2 Response: Part I
We thank Reviewer TPxR for clarifying the remaining concerns. We have conducted additional evaluations of radar support in reasoning rationale during inference (in addition to the support claim evaluation during training, reported in our earlier response) and comparisons between our CRP (claim-based projection) and generic rewriting.
Please also see the revised PDF of the main paper, including updated appendices, for more detailed new results and analyses, with changes highlighted in blue.
1. Baseline comparability. We understand your concern that differences in teacher-call budget, rationale length, screening, and effective training samples may contribute to the observed gains. To address this, the revised paper includes additional comparisons that match specific factors and examine alternative rationale-generation procedures.
The radar comparisons below use the same 1,308 training questions and answers and the RadarQA-300 evaluation, with the student model and training settings fixed within each comparison. Results are averaged over three seeds.
| Comparison | Student | Deployment-CoT accuracy (%) ↑ | Projected-CoT accuracy (%) ↑ |
|---|---|---|---|
| Clean radar-only generation | Qwen3-VL-8B, full fine-tuning | 67.4 ± 1.3 | 72.4 ± 1.0 |
| Matched rationale length | Qwen3-VL-8B, LoRA | 64.7 ± 2.8 | 68.8 ± 0.5 |
see Table 1 and Section 7.1 and Table 8, Appendix J for more details.
Projected-CoT achieves higher accuracy in both comparisons. These experiments address selected sources of confounding, although teacher-call counts and generation/editing procedures are not jointly matched.
We have now also compared CRP with generic rewriting using the same privileged rationales and two teacher calls per example, with additional rationale editing omitted from both methods. This comparison more directly examines the contribution of the projection procedure, as detailed in point 4 of Part II below.
2. Reliability of reasoning. We understand this concern as whether Projected-CoT reduces reasoning statements that the deployment sensor cannot support. Appendix F of the revised paper provides an independent model evaluation of training rationales (Table 4) and a human-assisted audit (Table 5), as reported in our earlier response. We now extend this evaluation to the students’ own rationales during inference to assess whether the learned reasoning is also supported by radar measurements.
Human-assisted audit of training rationales. Table 5 of the revised paper reports the following radar-supported claim rates:
| Training rationales | Radar-supported claims (%) ↑ |
|---|---|
| Privileged-CoT | 28.1 |
| Projected-CoT | 79.3 |
These estimates combine automatic identification of unsupported appearance claims with human judgments on 22 sampled non-appearance claims from Projected-CoT and 32 from Privileged-CoT. Four annotators provide two judgments per claim. Human–human agreement is 88.1%, and agreement between humans and the automated claim evaluator is 83.2%.
New evaluation at inference. We examine the students’ own test rationales on the 259 of 300 test questions with checkable radar point clouds. We define a metric of decisive claim, the statement in the student’s reasoning rationale that most directly supports its answer. A claim is considered to be true when both model judges agree that all checkable statements match the radar measurements.
| Supervision | Decisive claims judged true (%) ↑ |
|---|---|
| Clean radar-only Deployment-CoT | 49.7 |
| Projected-CoT | 56.7 |
The two independent model judges agree on 96.3% of decisive-claim assessments. These evaluations provide evidence of radar support in both training and inference rationales generated by the student deployment model.
We thank Reviewer TPxR for recognizing the sensor-observability problem and the evaluations across radar and audio. We address CRP projection steps (W1), implementation (W2), baseline comparability (W3), claim support (W4), and cost (W5). Revisions are highlighted in blue in the revised paper.
W1 / Q1. Ablation of CRP Projection Steps.
We ablate CRP steps and deletion methods (motivated by Q4f5) on RadarQA-300 with Qwen3-VL-8B LoRA, three seeds (Section 7.4, new Table 7 in Appendix I).
ABSTRACT contributes most. Omitting it costs 21.9 points, versus 11.9 for REMOVE. Deletion alone is insufficient. KEEP + REMOVE trails all four steps by 14.4 points. Explicit HEDGE adds 0.8 points over the original prompt, which already permits hedging (Appendix G.3).
W2 / Q2. Teacher Models and Projection Implementation.
The projector Pd is a prompted LLM that receives the deployment observation, question, ground-truth answer, and privileged rationale, but not the privileged observation. It applies KEEP, ABSTRACT, HEDGE, or REMOVE to each claim. For 1,101 radar examples, Claude Sonnet 5 writes the privileged rationale, projected rationale, and Deployment-CoT. Claude Opus handles the other 207 and selected revisions. Gemini 3.6 Flash writes the audio rationales. Section 4 and new Table B.1 (Appendix B.1) clarify the procedure and teacher assignments. The full radar projection prompt is provided in new Appendix G.1, with other prompts in Appendix G.2.
W3 / Q3. Teacher Budget, Rationale Length, Screening, and Training Samples.
We clarify differences in teacher calls, rationale length, selection procedures, and effective training samples (Table 1, new Table B.1 in Appendix B.1).
The original Deployment-CoT uses an independent radar-only interpretation and Projected-CoT as references. Both methods undergo consistency checks, which drop 566 candidates. An additional model-based screen rejects 47 of 1,625 Deployment-CoT candidates. Rejected candidates are excluded, while selected rationales with violations are edited or rewritten. Both methods retain the same 1,308 training examples.
We also evaluate three Deployment-CoT variants (three seeds):
Projected-CoT leads in all comparisons (Section 7.1, Appendix B.1, Appendix J). The clean radar baseline uses one teacher call versus two for Projected-CoT.
W4 / Q4. Independent Evaluation of Claim Support.
In the new Appendix F (Tables 4 and 5), an independent GPT-6.1 evaluator assesses 400 radar training examples across the three supervision methods without seeing the answer, RGB, or method identity. Four human annotators separately assess sampled non-appearance claims. Appearance claims are counted as unsupported by radar.
Projected-CoT has the highest supported-claim share. Human agreement is 88.1% for paired yes/no judgments. Human-assisted rates include automatically flagged appearance claims as unsupported.
W5 / Q5. Computational Cost and Scalability.
For radar, projection adds one teacher call per example after privileged-rationale generation and no additional work during student training or deployment. Each projection averages 1,803 input tokens, 396 output tokens, and 5.2 seconds. Projecting 1,308 examples takes about 14 minutes with eight parallel requests.
For Qwen3.5-4B, Projected-CoT uses 1.16M supervision tokens per run, compared with 1.50M for Deployment-CoT. Estimated five-run SFT costs are $4.29 for Projected-CoT, compared with $5.52 for Deployment-CoT (new Table B.1, Appendix B.1).
Projection cost grows linearly with training-set size. Evaluation covers two sensor gaps and five students, while larger-scale validation remains future work.