- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
HAIR interleaves latent blocks with compact textual checkpoints and applies goal-boundary distillation from a shared-weight explicit reasoning path. Experiments show substantial inference savings over full CoT. Paired ablations indicate that the checkpoint-only variant preserves most accuracy, while latent blocks and distillation provide no consistent improvement.
Critical strengths
- The paired ablations and multi-seed experiments provide useful evidence on the effects of latent blocks and distillation.
- The paper is clearly written, with well-organized figures and tables that make the method and results easy to follow.
Critical weaknesses
- The checkpoints constitute compact explicit CoT, while latent blocks and GBD provide no consistent benefit. Without comparisons against standard equation-only or compressed-CoT training, the substantive contribution remains unclear.
- The low CODI (18.95%) and Coconut (28.28%) results rely on single-seed runs without reported tuning or convergence evidence. Inconsistent training descriptions between Section 4.1 and Appendix G further weaken confidence in the claimed 30-point advantage.
Questions for authors
- Could the authors compare HAIR with standard equation-only or compressed-CoT training, including checkpoint-only SFT without the auxiliary rationale objective?
Dear Reviewer iuoi,
Could you read the responses from the authors and post your opinions after rebuttal? The authors think they may resolve your concerns and your comments should provide more details. You can post your idea about this paper. Any discussion is welcome.
Thanks,
AC