IAAR-Shanghai/xVerify-14B-Ia

<h1 align="center"> 🔍 xVerify-14B-Ia </h1>

<p align="center"> <div style="display: flex; justify-content: center; gap: 10px;"> <a href="https://github.com/IAAR-Shanghai/xVerify"> <img src="https://img.shields.io/badge/GitHub-Repository-blue?logo=github" alt="GitHub"/> </a> <a href="https://huggingface.co/IAAR-Shanghai/xVerify-14B-Ia"> <img src="https://img.shields.io/badge/🤗%20Hugging%20Face-xVerify--14B--Ia-yellow" alt="Hugging Face"/> </a> <a href="https://huggingface.co/papers/2504.10481"> <img src="https://img.shields.io/badge/Paper-HF%20Paper-red?logo=huggingface" alt="Paper"/> </a> </div> </p>

xVerify is an evaluation tool fine-tuned from a pre-trained large language model, designed specifically for objective questions with a single correct answer. It accurately extracts the final answer from lengthy reasoning processes and efficiently identifies equivalence across different forms of expressions.

This model was presented in the paper xVerify: Efficient Answer Verifier for Reasoning Model Evaluations.

✨ Key Features

📊 Broad Applicability

Suitable for various objective question evaluation scenarios including math problems, multiple-choice questions, classification tasks, and short-answer questions.

⛓️ Handles Long Reasoning Chains

Effectively processes answers with extensive reasoning steps to extract the final answer, regardless of complexity.

🌐 Multilingual Support

Primarily handles Chinese and English responses while remaining compatible with other languages.

🔄 Powerful Equivalence Judgment

• —✓ Recognizes basic transformations like letter case changes and Greek letter conversions
• —✓ Identifies equivalent mathematical expressions across formats (LaTeX, fractions, scientific notation)
• —✓ Determines semantic equivalence in natural language answers
• —✓ Matches multiple-choice responses by content rather than just option identifiers

🚀 Usage

To use xVerify for answer verification, you can follow the implementation provided in the official GitHub repository. Below is an example of single-sample evaluation:

from src.xVerify.model import Model
from src.xVerify.eval import Evaluator

# initialization
model_name = 'xVerify-14B-Ia'
model_path = 'IAAR-Shanghai/xVerify-14B-Ia'
inference_mode = 'local' # or 'api'

model = Model(
    model_name=model_name,
    model_path_or_url=model_path,
    inference_mode=inference_mode
)
evaluator = Evaluator(model=model)

# input evaluation information
question = "In which year did Fayaz A. Malik receive the Young Scientist of the Year from the Council of Scientific and Industrial Research?"
llm_output = "The year Fayaz A. Malik received the Young Scientist of the Year award from the Council of Scientific and Industrial Research was 2001.

The answer is 2001."
correct_answer = "2009"

# evaluation
result = evaluator.single_evaluate(
    question=question,
    llm_output=llm_output,
    correct_answer=correct_answer
)
print(result) # Output: Incorrect

📚 Citation

@article{xVerify,
      title={xVerify: Efficient Answer Verifier for Reasoning Model Evaluations}, 
      author={Ding Chen and Qingchen Yu and Pengyuan Wang and Wentao Zhang and Bo Tang and Feiyu Xiong and Xinchi Li and Minchuan Yang and Zhiyu Li},
      journal={arXiv preprint arXiv:2504.10481},
      year={2025},
}