metadata
license: cc-by-sa-4.0
language:
- en
This is a FilCo context filtering model for knowledge-grounded dialog generation tasks, particularly in the open domain. Specifically, this is a meta-llama/Llama-2-7b trained using LoRA for 3 epochs on the Wizard of Wikipedia (WoW) training set.
It is intended to be used in FilCo: https://github.com/zorazrw/filco, but can be further applied in similar scenarios.
Citation
if you use this model for research, please cite:
@article{wang2023learning,
title={Learning to Filter Context for Retrieval-Augmented Generation},
author={Zhiruo Wang, Jun Araki, Zhengbao Jiang, Md Rizwan Parvez, Graham Neubig},
journal={arXiv preprint arXiv:2311.08377},
year={2023}
}