---
pipeline_tag: text-ranking
library_name: transformers
license: apache-2.0
---

# Budget-Aware Test-Time Scaling via Discriminative Verification

This repository contains the `verification-1.5b` model, implementing the discriminative verifier described in the paper:
[**Budget-Aware Test-Time Scaling via Discriminative Verification**](https://huggingface.co/papers/2510.14913)

<p align="center">
  📃 <a href="https://arxiv.org/abs/2510.14913" target="_blank">[Paper on arXiv]</a> • 💻 <a href="https://github.com/wang-research-lab/verification" target="_blank">[GitHub]</a> • 🤗 <a href="https://huggingface.co/collections/WangResearchLab/verification-68f1abb00d7f3f7ef6e83ff3" target="_blank">[Hugging Face Collection]</a>
</p>

## Model Description

This model is a discriminative verifier designed for budget-aware test-time scaling in large language models on complex reasoning tasks. While state-of-the-art approaches often employ generative verifiers, this model shifts focus to a more budget-aware paradigm: discriminative verification. Empirical analysis demonstrates that combining discriminative verifiers with self-consistency creates a powerful and efficient test-time scaling mechanism, surpassing state-of-the-art generative verification under a fixed compute budget. This approach is not only a "free" upgrade over self-consistency but also a more effective and efficient alternative to costly generative techniques for practical, real-world applications.

## Usage

You can use this model to score candidate solutions for various evaluation datasets.

First, ensure you have the necessary environment set up by installing the package:

```bash
conda create -n verification python=3.10
conda activate verification
pip install -e . # This installs the 'verification' package and its dependencies
```

Then, you can run verification on an evaluation dataset (e.g., `aime2024`, `aime2025`, `livebench-math`, or `gpqa`) with the trained verifier using the `run_judge_hf.py` script:

```bash
python scripts/run_judge_hf.py \
    --model_name "WangResearchLab/verification-1.5b" \
    --dataset_name "verification-evaluation-data" \
    --dataset_split "validation" \
    --save_path "evals/verification-1.5b/validation-eval.jsonl" \
    --num_gpus 8
```

This command will score candidate solutions with the `WangResearchLab/verification-1.5b` model and save the evaluation results to the specified path.

## Citation

If you find this work useful, please consider citing the paper:

```bibtex
@article{montgomery2025budget,
  title={Budget-Aware Test-Time Scaling via Discriminative Verification},
  author={Montgomery, Kyle and Tan, Sijun and Chen, Yuqi and Zhuang, Siyuan and Zhang, Tianjun and Popa, Raluca Ada and Wang, Chenguang},
  journal={arXiv preprint arXiv:2510.14913},
  year={2025}
}
```