- Rating
- 3
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes Dr. Post-Training, which reexamines data selection in LLM post-training from a data-regularization perspective. The authors unify existing methods through a projection framework and introduce Group-Wise Subset Update. The paper also provides bias-variance analysis, convergence proofs, and an efficient implementation, with evaluations across SFT, RLHF, and RLVR.
Critical strengths
- The paper interprets data selection from a data-regularization perspective and unifies different training strategies within a feasible-set projection framework. This perspective is insightful and also suggests new ways to design data-selection methods.
- The authors characterize different update strategies using bias and exposed variance, and connect one-step errors to convergence. This provides a theoretical basis for understanding training stability when target data are scarce.
- The paper not only proposes a method but also optimizes gradient computation and memory overhead. The experimental design is also fairly thorough.
Critical weaknesses
Main Concerns
- GAST [1] also uses target-gradient alignment to select different training samples for different layers, but this work is not discussed. The two methods differ in selection strategies and system implementations. I suggest that the authors discuss this work and compare the methods under matched training conditions. This would clarify the algorithmic contribution and the settings where different selection strategies are appropriate.
- The paper's main theoretical guarantees are based on exact projection, but the implementation uses a Top-k approximation and ignores the gradient-redundancy term in the projection objective. In addition, the theoretical analysis considers direct gradient updates, while the experiments use AdamW. Under the paper's setting of (n = 8, k = 4), exact selection involves only 70 candidate combinations.
- The authors use ablations on partition granularity and target-set size to support the theoretical conclusions, but they do not directly measure the proposed bias and exposed variance. Thus, the current experiments mainly demonstrate that the method is effective, rather than sufficiently validating its theoretical mechanism. Minor Concern The evaluated models are mainly in the 1B-3B range, and the system tests use relatively controlled configurations. I suggest adding end-to-end training results on larger models.
Questions for authors
- GAST uses a gradient-alignment-based sampling strategy, whereas this paper mainly uses Top-k. Have the authors compared their performance and overhead under the same training budget? In which settings is Top-k preferable?
- Under the setting of (n = 8, k = 4), how much do the Top-k selections differ from exact projection? Does this difference affect downstream performance?
- Can the authors provide empirical estimates of bias and exposed variance? [1] Yao, K., Song, Z., Wu, K., Zhong, M., Cheng, D., Tan, Z., Ji, Y., & Gao, P. (2026). GAST: Gradient-aligned Sparse Tuning of Large Language Models with Data-layer Selection. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics, 4401-4416.
Dear Reviewer g6Xs,
As the author–reviewer discussion period draws to a close, we would appreciate your feedback on our responses and whether they address your concerns. We welcome any further questions or points for clarification. Thank you for your time and consideration.