After last year's successful BabyLM Challenge, the competition will be hosted again in 2024/2025. The overarching goals of the challenge remain the same; however, some of the competition rules will be different. The big changes for this year's competition are as follows: First, we replace the loose track with a paper track, which allows (for example) non-model-based submissions, novel cognitively-inspired benchmarks, or analysis techniques. Second, we are relaxing the rules around pretraining data, and will now allow participants to construct their own datasets provided they stay within the 100M-word or 10M-word budget. Third, we introduce a multimodal vision-and-language track, and will release a corpus of 50% text-only and 50% image-text multimodal data as a starting point for LM model training. The purpose of this CfP is to provide rules for this year's challenge, explain these rule changes and their rationale in greater detail, give a timeline of this year's competition, and provide answers to frequently asked questions from last year's challenge.
@article{DBLP:journals/corr/abs-2404-06214,
author = {Leshem Choshen and
Ryan Cotterell and
Michael Y. Hu and
Tal Linzen and
Aaron Mueller and
Candace Ross and
Alex Warstadt and
Ethan Wilcox and
Adina Williams and
Chengxu Zhuang},
title = {[Call for Papers] The 2nd BabyLM Challenge: Sample-efficient pretraining
on a developmentally plausible corpus},
journal = {CoRR},
volume = {abs/2404.06214},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2404.06214},
doi = {10.48550/ARXIV.2404.06214},
eprinttype = {arXiv},
eprint = {2404.06214},
timestamp = {Wed, 15 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2404-06214.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
See the full reference list in the paper.