---
base_model:
- princeton-nlp/Sheared-LLaMA-1.3B
datasets:
- ChilleD/MultiArith
license: llama2
pipeline_tag: text-generation
library_name: pytorch
arxiv: 2510.24940
tags:
- model_hub_mixin
- pytorch_model_hub_mixin
- chain-of-thought
- implicit-reasoning
---

# 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 ("implicit tokens") instead of generating long textual explanations. This approach significantly speeds up inference while maintaining high reasoning performance.

This specific checkpoint is **Sheared-LLaMA-1.3B** fine-tuned using the SemCoT framework on the **MultiArith** dataset.

- **Paper:** [SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens](https://huggingface.co/papers/2510.24940)
- **Code:** [Official GitHub Repository](https://github.com/YinhanHe123/SemCoT)

## 🎯 Key Features
- 🗣️ **Semantic Alignment**: Uses a contrastively trained sentence transformer to ensure that implicit reasoning tokens remain 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 is the first approach to jointly optimize both token-level generation speed and semantic alignment with ground-truth reasoning.

## 🛠️ Usage
To use this model, please refer to the [official implementation on GitHub](https://github.com/YinhanHe123/SemCoT/) as it requires the SemCoT framework to handle the implicit reasoning tokens correctly.

## Citation
```bibtex
@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}
}
```