metadata
license: mit
This repository contains the checkpoint for the corrector of LIFE, which is trained on the systhetic data for factual error correction with gold evidence. Please refer to the code of LIFE at https://github.com/NLPCode/LIFE for more details.
Usage
# Load the model
from transformers import AutoConfig, AutoModelForSeq2SeqLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("He-Xingwei/LIFE-Corrector-GE")
model = AutoModelForSeq2SeqLM.from_pretrained("He-Xingwei/LIFE-Corrector-GE")
Citation
If you want to use this model in your research, please cite our paper:
@inproceedings{he2024improving,
title={Improving Factual Error Correction by Learning to Inject Factual Errors},
author={He, Xingwei and Zhang, Qianru and Jin, A-Long and Ma, Jun and Yuan, Yuan and Yiu, Siu Ming},
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
volume={38},
number={16},
pages={18197--18205},
year={2024}
}