Add arxiv ID and improve model card

README.md

@@ -1,32 +1,43 @@
 ---
-license: llama2
-datasets:
-- ChilleD/MultiArith
 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 instead of generating long textual explanations. This implicit reasoning greatly speeds up inference while keeping performance high. Specifically, we take princeton-nlp/Sheared-LLaMA-1.3B as the base model and fine tune using the SemCoT framework on ChilleD/MultiArith dataset. See [our paper](https://arxiv.org/abs/2510.24940) and [our code](https://github.com/YinhanHe123/SemCoT/). Please reference the code for how to load and use the model.
+**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.
 
-## 🎯 Key Features
-🗣️ Semantic Alignment: Uses a contrastively trained sentence transformer to ensure that implicit reasoning remains semantically consistent with human-readable CoT explanations.
+This specific checkpoint is **Sheared-LLaMA-1.3B** fine-tuned using the SemCoT framework on the **MultiArith** dataset.
 
-⚡ Efficiency Optimization: Introduces a lightweight implicit reasoning generator, fine-tuned via knowledge distillation, to reduce token generation time and enhance inference speed.
+- **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.
 
-🧩 Joint Optimization: SemCoT simultaneously optimizes for reasoning speed and semantic alignment.
+## 🛠️ 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
-```
-@article{he2025semcot,
+```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},
-  journal={arXiv preprint arXiv:2510.24940},
+  booktitle={39th Conference on Neural Information Processing Systems (NeurIPS 2025)},
   year={2025}
 }
 ```