| --- |
| library_name: transformers |
| license: apache-2.0 |
| datasets: |
| - UCSC-VLAA/STAR-1 |
| base_model: |
| - deepseek-ai/DeepSeek-R1-Distill-Qwen-32B |
| --- |
| |
| # 🌟 STAR-1: Safer Alignment of Reasoning LLMs with 1K Data |
|
|
| <p align="center"> |
| 📃 <a href="https://arxiv.org/abs/2504.01903" target="_blank">Paper</a> ｜🤗 <a href="https://huggingface.co/datasets/UCSC-VLAA/STAR-1" target="_blank">STAR-1 Data</a> | 🤗 <a href="https://huggingface.co/collections/UCSC-VLAA/star-1-67edda2a042e8ba3e955e522" target="_blank">STAR-1 Model</a> | 📚 <a href="https://ucsc-vlaa.github.io/STAR-1/" target="_blank">Project Page</a> |
| </p> |
|
|
| ## Introduction |
| [**STAR-1**](https://huggingface.co/datasets/UCSC-VLAA/STAR-1) is a high-quality safety dataset designed to enhance safety alignment in large reasoning models (LRMs) like DeepSeek-R1. |
|
|
| - Built on the principles of diversity, deliberative reasoning, and rigorous filtering, STAR-1 integrates and refines data from multiple sources to provide policy-grounded reasoning samples. |
| - The dataset contains **1,000** carefully selected examples, each aligned with best safety practices through GPT-4o-based evaluation. |
| - Fine-tuning with STAR-1 leads to significant safety improvements across multiple benchmarks, with minimal impact on reasoning capabilities. |
|
|
| We open-sourced our [STAR1-R1-Distill-32B](https://huggingface.co/UCSC-VLAA/STAR1-R1-Distill-32B) model here, which is fine-tuned on [STAR-1](https://huggingface.co/datasets/UCSC-VLAA/STAR-1) dataset. |
|
|
| ## Artifacts |
| ### Data |
|
|
| | Dataset | Num. of Sample | URL | |
| |------------|----------------|----------------------------------------------------------------------| |
| | STAR-1 | 1K | 🤗 [UCSC-VLAA/STAR-1](https://huggingface.co/datasets/UCSC-VLAA/STAR-1) | |
| | STAR 41K | 41K | 🤗 [UCSC-VLAA/STAR-41K](https://huggingface.co/datasets/UCSC-VLAA/STAR-41K) | |
| | STAR-benign-915 | 915 | 🤗 [UCSC-VLAA/STAR-benign-915](https://huggingface.co/datasets/UCSC-VLAA/STAR-benign-915) | |
|
|
|
|
|
|
| ### Model |
| | Model | Type | URL | |
| |--------------------------------|-------------------------------------------|----------------------------------------------------------------------------------------| |
| | `STAR1`-R1-Distill-1.5B | R1-Distill-Qwen-1.5B trained on STAR-1 | 🤗 [UCSC-VLAA/STAR1-R1-Distill-1.5B](https://huggingface.co/UCSC-VLAA/STAR1-R1-Distill-1.5B) | |
| | `STAR1`-R1-Distill-7B | R1-Distill-Qwen-7B trained on STAR-1 | 🤗 [UCSC-VLAA/STAR1-R1-Distill-7B](https://huggingface.co/UCSC-VLAA/STAR1-R1-Distill-7B) | |
| | `STAR1`-R1-Distill-8B | R1-Distill-Llama-8B trained on STAR-1 | 🤗 [UCSC-VLAA/STAR1-R1-Distill-8B](https://huggingface.co/UCSC-VLAA/STAR1-R1-Distill-8B) | |
| | `STAR1`-R1-Distill-14B | R1-Distill-Qwen-14B trained on STAR-1 | 🤗 [UCSC-VLAA/STAR1-R1-Distill-14B](https://huggingface.co/UCSC-VLAA/STAR1-R1-Distill-14B) | |
| | `STAR1`-R1-Distill-32B | R1-Distill-Qwen-32B trained on STAR-1 | 🤗 [UCSC-VLAA/STAR1-R1-Distill-32B](https://huggingface.co/UCSC-VLAA/STAR1-R1-Distill-32B) | |
|
|
| ## Evaluation |
| See our github [repo](https://github.com/UCSC-VLAA/STAR-1?tab=readme-ov-file#evaluation-sec-31). |
|
|
| ## Acknowledgement |
| This work is partially supported by a gift from Open Philanthropy. We thank the NAIRR Pilot Program and the Microsoft Accelerate Foundation Models Research Program for supporting our computing needs. |
|
|
|
|
| ## Citation |
| ``` |
| @article{wang2025star1saferalignmentreasoning, |
| title={STAR-1: Safer Alignment of Reasoning LLMs with 1K Data}, |
| author={Zijun Wang and Haoqin Tu and Yuhan Wang and Juncheng Wu and Jieru Mei and Brian R. Bartoldson and Bhavya Kailkhura and Cihang Xie}, |
| year={2025}, |
| journal = {arXiv preprint arXiv:2504.01903} |
| } |
