← all papers · overview

Improve Student's Reasoning Generalizability Through Cascading Decomposed Cots Distillation

Abstract

Large language models (LLMs) exhibit enhanced reasoning at larger scales, driving efforts to distill these capabilities into smaller models via teacher-student learning. Previous works simply fine-tune student models on teachers' generated Chain-of-Thoughts (CoTs) data. Although these methods enhance in-domain (IND) reasoning performance, they struggle to generalize to out-of-domain (OOD) tasks. W

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).