Lil-Bevo: Explorations of Strategies for Training Language Models in More Humanlike Ways

Venkata S Govindarajan, Juan Diego Rodriguez, Kaj Bostrom, Kyle Mahowald


Anthology ID:
2023.conll-babylm.27
Volume:
Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning
Month:
December
Year:
2023
Address:
Singapore
Editors:
Alex Warstadt, Aaron Mueller, Leshem Choshen, Ethan Wilcox, Chengxu Zhuang, Juan Ciro, Rafael Mosquera, Bhargavi Paranjabe, Adina Williams, Tal Linzen, Ryan Cotterell
Venue:
CoNLL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
308–316
Language:
URL:
https://aclanthology.org/2023.conll-babylm.27
DOI:
10.18653/v1/2023.conll-babylm.27
Bibkey:
Cite (ACL):
Venkata S Govindarajan, Juan Diego Rodriguez, Kaj Bostrom, and Kyle Mahowald. 2023. Lil-Bevo: Explorations of Strategies for Training Language Models in More Humanlike Ways. In Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning, pages 308–316, Singapore. Association for Computational Linguistics.
Cite (Informal):
Lil-Bevo: Explorations of Strategies for Training Language Models in More Humanlike Ways (Govindarajan et al., CoNLL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.conll-babylm.27.pdf