SYNLAT: Syntax-Aligned Text-Latent Compression for Chain-of-Thought Reasoning
This work introduces SynLat, a text-latent CoT framework that aligns compression boundaries with syntactic structure through non-overlapping Syntax-Aligned Units (SAUs) and generates mixed reasoning from only the question and requested compression level at inference.
Yi-Feng Zhao, Hong-Jun Yu, Shi-Bo Wang et al.
· 0 citations