AINeutralarXiv – CS AI · 9h ago6/10
🧠
Structural Rationale Distillation via Reasoning Space Compression
Researchers propose Distillation through Reasoning Path Compression (D-RPC), a method that improves how large language models teach smaller ones by constraining teacher models to follow a curated bank of consistent reasoning strategies. The approach reduces noisy supervision while maintaining reasoning diversity, outperforming existing distillation methods across math and commonsense reasoning benchmarks.