jonathanhe123/SemCoT-Sheared-LLaMA-1.3B-coin_flip

SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens

🚀 Overview

SemCoT is a framework that improves the efficiency of Chain-of-Thought (CoT) reasoning by encoding reasoning steps inside hidden representations instead of generating long textual explanations. This implicit reasoning greatly speeds up inference while keeping performance high.

Specifically, this checkpoint is a fine-tuned version of princeton-nlp/Sheared-LLaMA-1.3B using the SemCoT framework on the skrishna/coin_flip dataset.

• Paper: SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens
• Code: Official GitHub Repository

🎯 Key Features

• 🗣️ Semantic Alignment: Uses a contrastively trained sentence transformer to ensure that implicit reasoning remains semantically consistent with human-readable CoT explanations.
• ⚡ Efficiency Optimization: Introduces a lightweight implicit reasoning generator, fine-tuned via knowledge distillation, to reduce token generation time and enhance inference speed.
• 🧩 Joint Optimization: SemCoT simultaneously optimizes for reasoning speed and semantic alignment.

Citation

If you find this work useful, please cite our paper:

@inproceedings{he2025semcot,
  title={SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens},
  author={He, Yinhan and Zheng, Wendy and Zhu, Yaochen and Zheng, Zaiyi and Su, Lin and Vasudevan, Sriram and Guo, Qi and Hong, Liangjie and Li, Jundong},
  booktitle={39th Conference on Neural Information Processing Systems (NeurIPS 2025)},
  year={2025}
}