---
base_model: Qwen/Qwen3-8B
language:
- en
library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
datasets:
- Jingleqian/AAPA-data
tags:
- alignment
- grpo
- aapa
- qwen
- instruction-following
---

# AAPA-8B

This repository contains the 8B A-GRPO checkpoint released with **AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models**.

AAPA is a plug-in framework that augments post-training objectives with a sentence-level adversarial anchoring signal. It compares policy rollouts with offline expert responses using a fixed lightweight discriminator, providing semantic grounding during preference optimization.

This checkpoint is trained from [Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) using the AAPA code release.

## Resources

- Paper: https://arxiv.org/abs/2509.25148
- Hugging Face Paper: https://huggingface.co/papers/2509.25148
- Code: https://github.com/IsFaqq/AAPA
- Data: https://huggingface.co/datasets/Jingleqian/AAPA-data
- 0.6B checkpoint: https://huggingface.co/Jingleqian/AAPA-06B

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Jingleqian/AAPA-8B"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
```

## Citation

```bibtex
@article{aapa2025,
  title={AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models},
  author={Faqiang Qian and Kang An and Weikun Zhang and Ziliang Wang and Xuhui Zheng and Liangjian Wen and Yong Dai and Mengya Gao and Yichao Wu},
  journal={arXiv preprint arXiv:2509.25148},
  year={2025}
}
```