Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers
Paper • 2506.13342 • Published
How to use just1nseo/ClearCheck-8B with Transformers:
# Use a pipeline as a high-level helper
# Warning: Pipeline type "question-answering" is no longer supported in transformers v5.
# You must load the model directly (see below) or downgrade to v4.x with:
# pip install "transformers<5.0.0"
from transformers import pipeline
pipe = pipeline("question-answering", model="just1nseo/ClearCheck-8B") # pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("just1nseo/ClearCheck-8B")
model = AutoModelForCausalLM.from_pretrained("just1nseo/ClearCheck-8B", device_map="auto")This repository contains the ClearCheck-8B model presented in the paper Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers.
Code: https://github.com/just1nseo/Verifying-the-Verifiers
If you find this model useful, please cite our paper!
@article{seo2025verifying,
title={Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers},
author={Seo, Wooseok and Han, Seungju and Jung, Jaehun and Newman, Benjamin and Lim, Seungwon and Lee, Seungbeen and Lu, Ximing and Choi, Yejin and Yu, Youngjae},
journal={arXiv preprint arXiv:2506.13342},
year={2025}
}