@inproceedings{bhardwaj-etal-2023-pre,
title = "Pre-training {LLM}s using human-like development data corpus",
author = "Bhardwaj, Khushi and
Shah, Raj Sanjay and
Varma, Sashank",
editor = "Warstadt, Alex and
Mueller, Aaron and
Choshen, Leshem and
Wilcox, Ethan and
Zhuang, Chengxu and
Ciro, Juan and
Mosquera, Rafael and
Paranjabe, Bhargavi and
Williams, Adina and
Linzen, Tal and
Cotterell, Ryan",
booktitle = "Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.conll-babylm.30/",
doi = "10.18653/v1/2023.conll-babylm.30",
pages = "339--345"
}
Markdown (Informal)
[Pre-training LLMs using human-like development data corpus](https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.conll-babylm.30/) (Bhardwaj et al., CoNLL-BabyLM 2023)
ACL
- Khushi Bhardwaj, Raj Sanjay Shah, and Sashank Varma. 2023. Pre-training LLMs using human-like development data corpus. In Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning, pages 339–345, Singapore. Association for Computational Linguistics.