Kim et al.
Cross-feedback and step-wise scoring let small models match much larger reasoning datasets
The authors' CRD framework iteratively critiques multiple teachers, scores individual reasoning steps, and stitches complementary chains to train compact models on 50K examples.
Top University
Taehoon Kim · Seunggeun Cho · Dongsu Han
KAIST
Research Digest··2 min read
Kim, Cho, and Han propose Collaborative Reasoning Distillation (CRD), a multi-teacher distillation framework combining interactive cross-feedback, step-level quality assessment, and coherence-aware chain stitching.
Why this paper
From KAIST
In one line
CRD-4B achieves 97.3% on MATH-500 and 70.3% on AIME'25 using only 50K training examples.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks (3 benchmarks)
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§