Catch Me If You Can: How Smaller Reasoning Models Pretend to Reason with Mathematical Fidelity

This article likely discusses the techniques used by smaller language models to mimic the reasoning capabilities of larger models, specifically focusing on mathematical reasoning. The title suggests a critical examination of these methods, implying that the 'reasoning' might be superficial or deceptive. The source, ArXiv, indicates this is a research paper, suggesting a technical and in-depth analysis.