Improve model card: Add metadata, paper and code links, and citation

README.md

@@ -1,6 +1,14 @@
+---
+license: mit
+library_name: transformers
+pipeline_tag: text-generation
+---
+
 # CSQA GPT2-Large Context-Aware Model
 
-This model is a GPT2-large based model fine-tuned for the CommonsenseQA (CSQA) task with context-aware capabilities.
+This model is a GPT2-large based model fine-tuned for the CommonsenseQA (CSQA) task with context-aware capabilities. It is part of the "Let's Predict Sentence by Sentence" framework, presented in the paper [Let's Predict Sentence by Sentence](https://huggingface.co/papers/2505.22202) (arXiv:2505.22202). This work investigates adapting pretrained token-level Language Models to operate in sentence space by autoregressively predicting continuous embeddings of next sentences, enabling abstract reasoning.
+
+For the official implementation and further details, please refer to the [GitHub repository](https://github.com/hbin0701/pred-sent).
 
 ## Model Architecture
 
@@ -22,8 +30,26 @@ This is a multi-component model that includes:
 
 ## Usage
 
-This model was trained for the CommonsenseQA task and includes specialized components for context-aware reasoning.
+This model was trained for the CommonsenseQA task and includes specialized components for context-aware reasoning. For detailed usage, particularly with the SentenceLens visualization tool or the full training pipeline, please refer to the [GitHub repository](https://github.com/hbin0701/pred-sent).
 
 ## Training
 
-The model was trained in multiple stages on the CommonsenseQA dataset, incorporating context-aware mechanisms to improve reasoning capabilities. 
+The model was trained in multiple stages on the CommonsenseQA dataset, incorporating context-aware mechanisms to improve reasoning capabilities. More details on the training pipeline (SFT, Embedding Training, Latent Model Training) can be found in the [GitHub repository](https://github.com/hbin0701/pred-sent) and the [paper](https://huggingface.co/papers/2505.22202).
+
+## Citation
+
+If you find this work useful in your research, please cite our paper:
+
+```bibtex
+@misc{hwang2025letspredictsentencesentence,
+      title={Let's Predict Sentence by Sentence}, 
+      author={Hyeonbin Hwang and Byeongguk Jeon and Seungone Kim and Jiyeon Kim 
+              and Hoyeon Chang and Sohee Yang and Seungpil Won and Dohaeng Lee 
+              and Youbin Ahn and Minjoon Seo},
+      year={2025},
+      eprint={2505.22202},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2505.22202}
+}
+```