3 accepted papers
Knowledge distillation from powerful reasoning models underpins the development of Small Language Models (SLMs). A prevailing assumption in this paradigm is that training data with higher perceived quality, often defined by rigorous logic and superior reward scores, monotonically enhances downstream…
The Transformer architecture has revolutionized various fields since it was proposed, where positional encoding plays an essential role in effectively capturing sequential order and context. Therefore, Rotary Positional Encoding (RoPE) was proposed to alleviate these issues, which integrates positio…
Group Relative Policy Optimization (GRPO) fine-tuning has been empirically shown to significantly enhance the reasoning abilities of language models. However, it often relies on large-scale, high-quality labeled data, which is typically difficult to obtain. To address this challenge, we introduce th…