Optimizing Decomposition for Optimal Claim Verification
Paper • 2503.15354 • Published • 18
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("ylu610/FT-T5-3B-Verifier")
model = AutoModelForSeq2SeqLM.from_pretrained("ylu610/FT-T5-3B-Verifier", device_map="auto")Quick Links
The T5-3B model finetuned on FActScore dataset for the claim verification task. The model is used in our paper: Optimizing Decomposition for Optimal Claim Verification. If you find this model useful, please cite the paper:
@misc{lu2025optimizingdecompositionoptimalclaim,
title={Optimizing Decomposition for Optimal Claim Verification},
author={Yining Lu and Noah Ziems and Hy Dang and Meng Jiang},
year={2025},
eprint={2503.15354},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2503.15354},
}
- Downloads last month
- 16
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ylu610/FT-T5-3B-Verifier")