DenseSteer: Steering Small Language Models towards Dense Math Reasoning 事件

DenseSteer: Steering Small Language Models towards Dense Math Reasoning arXiv:2605.29247v1 Announce Type: cross Abstract: Large language models (LLMs) demonstrate strong chain-of-thought (CoT) reasoning abilities, while smaller models (<= 3B parameters) significantly underperform on multi-step reasoning tasks. Based on empirical analyses of the Qwen-2.5 model family on math reasoning benchmarks, we find that more proficient reasoning is associated with fewer reasoning steps but higher informati