D-RPC compresses reasoning into a dynamic bank of reusable paths to produce consistent teacher rationales, outperforming standard distillation baselines on five reasoning benchmarks while using fewer tokens.
ans". Output ONLY valid JSON (no markdown, no extra text): {
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Structural Rationale Distillation via Reasoning Space Compression
D-RPC compresses reasoning into a dynamic bank of reusable paths to produce consistent teacher rationales, outperforming standard distillation baselines on five reasoning benchmarks while using fewer tokens.