Want to create an interactive transcript for this episode?
Podcast: Arxiv Papers
Episode: Phi-4-Mini-Reasoning: Exploring the Limits of Small Reasoning Language Models in Math
Description: This work presents a systematic training recipe for Small Language Models, enhancing their reasoning capabilities using Chain-of-Thought data, outperforming larger models in math reasoning tasks.https://arxiv.org/abs//2504.21233YouTube: https://www.youtube.com/@ArxivPapersTikTok: https://www.tiktok.com/@arxiv_papersApple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers