Update README.md

README.md

@@ -1,68 +1,38 @@
 ---
-base_model: Thrillcrazyer/Qwen-7B_THIP
+
+datasets: DeepMath-103k
 library_name: transformers
 model_name: Qwen-7B_THIP
-tags:
-- generated_from_trainer
-- grpo
-- trl
 licence: license
 ---
 
-# Model Card for Qwen-7B_THIP
-
-This model is a fine-tuned version of [Thrillcrazyer/Qwen-7B_THIP](https://huggingface.co/Thrillcrazyer/Qwen-7B_THIP).
-It has been trained using [TRL](https://github.com/huggingface/trl).
-
-## Quick start
-
-```python
-from transformers import pipeline
-
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="Thrillcrazyer/Qwen-7B_THIP", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
+<h1 align= "center"> Reasoning-Aware GRPO using Process Mining </h1>
 
-## Training procedure
+<p align="center">
+  <a href="https://pnubaelab.github.io/"><b>BAELAB</b></a>, Pusan National University, Busan, Korea
+</p>
+<p align="center">
+  Taekyhun Park<sup>*</sup> , Yongjae Lee<sup>*</sup>, Hyerim Bae<sup>&dagger;</sup>
+</p>
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/pthpark1/TAC/runs/whtsmb9d) 
 
 
-This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
 
-### Framework versions
 
-- TRL: 0.27.0
-- Transformers: 4.57.6
-- Pytorch: 2.8.0
-- Datasets: 4.5.0
-- Tokenizers: 0.22.2
 
-## Citations
+<p align="center">
+  <a href="https://github.com/Thrillcrazyer/TACReward"><b>🌟 Github</b></a> |
+  <a href="https://huggingface.co/Thrillcrazyer/Qwen-1.5B_THIP"><b>📥 1.5B Download</b></a> |
+  <a href="https://huggingface.co/Thrillcrazyer/TACReward7B"><b>📥 7B Download</b></a> |
+  <a href="https://arxiv.org/abs/2510.25065"><b>📄 Arxiv Paper Link</b></a> |
+</p>
 
-Cite GRPO as:
+# Abstract
 
-```bibtex
-@article{shao2024deepseekmath,
-    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
-    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
-    year         = 2024,
-    eprint       = {arXiv:2402.03300},
-}
+Reinforcement learning (RL)-based post-training has been crucial for enabling multi-step reasoning in large reasoning models (LRMs), yet current reward schemes are typically outcome-centric. We propose **PM4GRPO**, a reasoning-aware Group Relative Policy Optimization (GRPO) that augments standard answer/format rewards with signals over the reasoning procedure. To this end, process mining techniques are utilized to compute a scalar conformance reward that measures how closely a policy model's reasoning aligns with the pretrained teacher model. The empirical results on five benchmarks demonstrate that **PM4GRPO** significantly outperforms existing methodologies for GRPO-based post-training. These results highlight that leveraging process mining for reasoning-aware GRPO effectively enhances the reasoning capabilities of policy models.
 
-```
+# Illustration of PM4GRPO
 
-Cite TRL as:
-    
-```bibtex
-@misc{vonwerra2022trl,
-	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
-	year         = 2020,
-	journal      = {GitHub repository},
-	publisher    = {GitHub},
-	howpublished = {\url{https://github.com/huggingface/trl}}
-}
-```
+<div align="center">
+<img src="https://arxiv.org/html/2510.25065v1/x1.png" width="600"/>
+</div>