conftrace_

long chain-of-thought training

1 paper

Explore in graph

Also known as

LONG COT

Co-occurring keywords · papers mentioning both

reasoning training (1) small language model (1) error accumulation (1) supervised fine-tuning (1) reinforcement learning (1)

Papers

Through the Valley: Path to Effective Long CoT Training for Small Language Models EMNLP 2025