- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes EM-OPD, an evidence-conditioned multi-expert on-policy distillation framework for pathology report generation. The method constructs multiple teacher experts from a shared frozen backbone, where each expert is conditioned on a different type of privileged pathological evidence (diagnosis, abnormality, glandular structure, or cellular morphology). The student generates on-policy trajectories, while the corresponding expert provides token-level supervision through Jensen-Shannon divergence. The expert objectives are then equally averaged through a balanced joint-consolidation objective. At inference time, the student uses only the pathology image and reporting prompt.
The paper evaluates EM-OPD on five pathology datasets and compares against general/pathology VLMs, SFT, and GRPO. The authors report substantial improvements, particularly for fine-grained cellular and abnormality-level evaluation, as well as additional out-of-domain results.
Critical strengths
-
Practical use of heterogeneous pathology supervision.
The paper provides a reasonable way to unify heterogeneous annotations such as regions, segmentation masks, diagnosis labels, and morphological information into a single report-generation student. The spatial-anchor + morphological-descriptor formulation is intuitive and practically relevant. -
Comprehensive empirical study.
The paper evaluates multiple pathology evidence types, several student/teacher sizes, SFT and GRPO baselines, cue ablations, multi-expert ablations, divergence choices, and out-of-domain performance. -
No additional inference-time expert cost.
Privileged evidence and expert teachers are used only during training; the final student retains a standard image-to-report inference interface.
Critical weaknesses
-
Limited methodological novelty relative to prior OPD work.
The core training formulation closely follows existing on-policy distillation: the student generates its own trajectories and a teacher provides token-level distribution supervision on those prefixes [1]. Privileged-information OPD has also already been extended to multimodal models, e.g., Vision-OPD [2], and on-policy distillation has recently been explored for medical VLM reasoning in OPVD [3]. The main novelty here therefore appears to be the pathology-specific construction of multiple evidence-conditioned experts and equal-weight consolidation, rather than a fundamentally new OPD framework. The Methods section should also more clearly distinguish inherited OPD components from newly proposed components. -
Missing comparison against prior medical/multimodal OPD methods.
The main training baselines are SFT and GRPO, but the paper does not compare against existing on-policy distillation methods for multimodal or medical reasoning [2,3]. Since the claimed contribution is specifically an extension of OPD to pathology with multiple experts, an OPD baseline is important to determine whether the gains come from on-policy distillation itself or from the proposed multi-expert design. -
Report-generation quality is not directly evaluated.
The authors state that no ground-truth pathology reports are available. Generated reports are therefore passed through Qwen3.5-27B to extract structured information, after which classification/F1/Mention Rate metrics are computed. This evaluates whether certain structured findings can be recovered from the report, but does not directly assess clinical correctness, completeness, coherence, hallucination, or overall report quality. If the target task is pathology report generation, I would expect either blinded pathologist evaluation or a validated clinical report-quality metric (e.g., a pathology-adapted GREEN-style evaluation). Otherwise, it is unclear why the task is formulated as open-ended report generation when both supervision and evaluation ultimately reduce to structured pathology annotations. -
The GRPO baseline is insufficiently specified.
GRPO is introduced as the RL baseline, but the paper does not clearly define the reward function used for pathology report generation or provide the corresponding training objective. Since GRPO performance is highly sensitive to reward design, this makes the comparison difficult to assess or reproduce. If the reward is adopted from prior work, the source should be cited; if it is newly designed, the reward formulation should be explicitly defined. -
Several design choices need stronger justification.
EM-OPD fixes the Jensen-Shannon mixture coefficient to 1/2. However, the original OPD/GKD work shows that divergence choice and JSD interpolation can be task-dependent and explicitly studies different values of the coefficient [1]. The appendix compares JSD with forward/reverse KL, but does not study sensitivity to this coefficient. In addition, the balanced consolidation strategy is simply an equal average of expert objectives; stronger comparison with adaptive multi-task/multi-expert weighting would help establish whether equal weighting is important.
References
[1] R. Agarwal et al., “On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes,” ICLR 2024.
https://proceedings.iclr.cc/paper_files/paper/2024/hash/5be69a584901a26c521c2b51e40a4c20-Abstract-Conference.html
[2] Q. Yuan et al., “Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation,” 2026.
https://arxiv.org/abs/2605.18740
[3] N. Zhang and Q. Yang, “OPVD: On-Policy Chain-of-Visual-Thought Distillation for Medical Reasoning,” MICCAI 2026.
https://papers.miccai.org/miccai-2026/0740-Paper3650.html
Questions for authors
- What is the methodological novelty beyond standard OPD/GKD, privileged multimodal OPD, and recent medical VLM on-policy distillation?
- Why are prior multimodal/medical OPD methods not included as baselines?
- What exact reward and optimization objective are used for the GRPO baseline?
- Given that no ground-truth reports exist, why is open-ended report generation chosen as the target task? Could the authors provide blinded pathologist evaluation or a validated clinical report-quality metric?
- How sensitive is performance to the JSD interpolation coefficient rather than fixing it to 1/2?
- How does balanced equal weighting compare with adaptive expert weighting or other multi-objective optimization strategies?
2 comments
Thank you for the authors' rebuttal. The feel like the experiment of values shows a mixed result on how the method generalizes. However, the biggest concern that I still have is the generalization of the EM-OPD algorithm that the authors provide. Authors frame their story as a novel and generalized algorithm but only limited to the pathology domain. If the algorithm is tested on more models and different domains (e.g, document report generation also requires multi-level hops and reasoning layers), it will be more convincing. If this work is submitted to MICCAI or any specialized conference that accepts novel pathology method, I would give a clear accept. However, at ICLR conference level, I think that the method should be tested on more domains and models to see the generalizability of the algorithm. Therefore, I still keep my score.
We sincerely appreciate the time and effort you dedicated to reviewing our work. Your comments have helped us improve the clarity of our work.
We agree that token-level supervision is an established OPD component. However, the central contribution of EM-OPD is an evidence-conditioned multi-expert framework that turns fragmented pathology annotations into supervision for reports covering multiple levels of pathological evidence. Our novelty therefore lies in the combination of multi-expert supervision, the use of otherwise fragmented annotations, and their consolidation toward multi-level report coverage.
We add a stronger OPD baseline, Vision-OPD, to further demonstrate the effectiveness of our method. For OPSD, the official code is not open-sourced.
As the table shows, EM-OPD outperforms Vision-OPD, which further demonstrates the effectiveness of our method.
We add a blinded pathologist review of 20 sampled cases each from BreakHis and Lizard and three-judge LLM evaluation across all five datasets (Sec. 4.3, Table 2). GPT-6.1 Sol, Gemini 3.8 Flash, and Claude Sonnet 5.5 independently score image–report pairs from 1–5. Both evaluations consider correctness, completeness, coherence, hallucinations, contradictions, and omissions.
As the table shows, our method outperforms most baselines in human evaluation. LLM evaluation likewise favors EM-OPD over the same-scale baselines. We further compute Spearman's rank correlation coefficient (ρ) using LLM scores on the same sampled image–report pairs evaluated by the experts. Table 7 in Appendix A.5 shows strong model-level rank correlation between expert and LLM scores on BreakHis (ρ=0.939) and Lizard (ρ=0.926). LLM scores also correlate positively with automatic metrics.
During GRPO training, we use the same extractor to convert the generated reports into structured findings, which are compared with the corresponding annotations to compute the GRPO reward. Eqs. (16)–(19) now specify the GRPO reward pipeline and objective.
We vary the mixture weight β under matched training settings (Appendix A.4, Table 6) and extend the original KL ablation.
Symmetric JSD achieves relatively better results, supporting it as a default optimal choice.
We also add GradNorm adaptive weighting (Sec. 4.4.2, Fig. 3).
Our method exceeds GradNorm on all five datasets. Compared with source-proportional weighting, it improves four datasets with a trade-off on GleasonXAI. This supports balancing reporting emphasis independently of annotation volume.