118 lines
5.4 KiB
Markdown
118 lines
5.4 KiB
Markdown
---
|
||
library_name: transformers
|
||
license: apache-2.0
|
||
license_link: https://github.com/foreverlasting1202/QuestA/blob/main/LICENSE
|
||
pipeline_tag: text-generation
|
||
|
||
---
|
||
|
||
# QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation
|
||
|
||
<p align="center">
|
||
| <a href="https://www.arxiv.org/abs/2507.13266"><b>Paper</b></a> | <a href="https://github.com/foreverlasting1202/QuestA/"><b>Documentation</b></a> | <a
|
||
href="https://mercurial-kidney-02d.notion.site/QuestA-Expanding-Reasoning-Capacity-in-LLMs-via-Question-Augmentation-216b21d08abb81a1bcecfe79e7d1e88a"><b>Blog</b></a> | <a
|
||
href="https://huggingface.co/foreverlasting1202/QuestA-Nemotron-1.5B"><b>🤗Models</b></a> | <a
|
||
href="https://huggingface.co/datasets/foreverlasting1202/QuestA"><b>🤗Datas</b></a> | <a
|
||
</p>
|
||
|
||
## Highlights
|
||
|
||
QuestA introduces **question augmentation** to significantly improve reasoning tasks in large language models (LLMs). By incorporating partial solutions during reinforcement learning (RL) training, QuestA enhances problem-solving capacity and accelerates learning on challenging tasks. Key improvements with **QuestA**:
|
||
|
||
- **Significant performance boost** on math reasoning benchmarks (e.g., AIME25, HMMT25), including a **10%+ increase** in accuracy.
|
||
- **Enhanced training efficiency** via augmented prompts, allowing more tractable learning on hard problems.
|
||
- **State-of-the-art results** for 1.5B-parameter models, making QuestA effective even on models with smaller parameter sizes.
|
||
|
||
|
||
|
||
|
||
|
||
|
||
## Model Overview
|
||
|
||
- **Model Type**: Causal Language Model (RL-based Training)
|
||
- **Training Method**: Reinforcement Learning (RL) with Question Augmentation
|
||
- **Number of Parameters**: 1.5B (base model), augmented with dynamic difficulty control
|
||
- **Layer Count**: Customizable based on the RL training configuration
|
||
- **Context Length**: 32K tokens (configurable)
|
||
- **Main Innovation**: Question Augmentation with Partial Solutions
|
||
|
||
QuestA dynamically adjusts problem difficulty by providing partial solutions to complex problems, thus improving the model’s ability to solve hard tasks more effectively.
|
||
|
||
## Performance
|
||
|
||
QuestA achieves the following performance improvements over baseline models, particularly in the field of math reasoning:
|
||
|
||
| Model | AIME24 | AIME25 | HMMT FEB 25 | Olympiad Bench | BRUMO25 | Avg. |
|
||
| ----------------------- | -------- | -------- | ----------- | -------------- | -------- | -------- |
|
||
| DeepSeek-R1-Distill-32B | **72.6** | 51.8 | 33.0 | 65.0 | 68.0 | 58.1 |
|
||
| Qwen3-1.7B | 48.3 | 36.8 | 22.2 | 56.1 | 44.1 | 41.5 |
|
||
| Nemotron-1.5B | 61.8 | 49.5 | 31.6 | 64.6 | 58.2 | 53.1 |
|
||
| *QuestA*-Nemotron-1.5B | 72.5 | **62.3** | **41.7** | **70.4** | **69.5** | **63.3** |
|
||
|
||
- **Pass@k Performance**: Shows consistent improvement across various difficulty levels.
|
||
|
||
## Quickstart
|
||
|
||
To get started with QuestA, you can load the model using the `transformers` library. Make sure you have the latest version installed.
|
||
|
||
```bash
|
||
pip install transformers
|
||
```
|
||
|
||
Example Python code to run QuestA:
|
||
|
||
```python
|
||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||
|
||
model_name = "QuestA/QuestA-Nemotron-1.5B"
|
||
|
||
# Load model and tokenizer
|
||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||
model = AutoModelForCausalLM.from_pretrained(model_name)
|
||
|
||
# Generate response with augmented question
|
||
prompt = "Solve for x: 2x + 3 = 11."
|
||
inputs = tokenizer(prompt, return_tensors="pt")
|
||
outputs = model.generate(**inputs)
|
||
|
||
# Decode the response
|
||
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
||
print(response)
|
||
```
|
||
|
||
For deployment, QuestA can be served using frameworks like **vLLM** or **SGLang**:
|
||
|
||
```bash
|
||
# For vLLM
|
||
vllm serve QuestA/QuestA-Nemotron-1.5B --tensor-parallel-size 8 --max-model-len 32768
|
||
```
|
||
|
||
## Key Features
|
||
|
||
- **Question Augmentation**: Prepend partial solutions to difficult problems, aiding model learning.
|
||
- **Curriculum-based RL**: Gradually reduce dependency on hints as training progresses.
|
||
- **Training with Augmented Data**: Use dynamically filtered datasets to focus on the hardest problems.
|
||
- **Efficient Learning**: Faster convergence on complex tasks due to better sampling and more informative rewards.
|
||
|
||
## Citation
|
||
|
||
If you find this work useful, please cite our paper:
|
||
|
||
```bibtex
|
||
@misc{li2025questaexpandingreasoningcapacity,
|
||
title={QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation},
|
||
author={Jiazheng Li and Hong Lu and Kaiyue Wen and Zaiwen Yang and Jiaxuan Gao and Hongzhou Lin and Yi Wu and Jingzhao Zhang},
|
||
year={2025},
|
||
eprint={2507.13266},
|
||
archivePrefix={arXiv},
|
||
primaryClass={cs.CL},
|
||
url={https://arxiv.org/abs/2507.13266},
|
||
}
|
||
```
|
||
|
||
For more details on the methodology, results, and code, visit the official [QuestA GitHub repository](https://github.com/foreverlasting1202/QuestA).
|
||
|
||
## Conclusion
|
||
|
||
QuestA is a novel framework for enhancing LLMs' reasoning capabilities by addressing complex problems more effectively. By augmenting the training process with partial solutions, QuestA accelerates learning, resulting in state-of-the-art performance on benchmark math reasoning tasks and more. |