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, we take optimum/mistral-1.1b-testing as the base model and fine tune using the SemCoT framework on tau/commonsense_qa dataset. See our paper and our code. Please reference the code for how to load and use the model.

🗣️ 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.

@article{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},
  journal={arXiv preprint arXiv:2510.24940},
  year={2025}
}