BabyLM Turns 3: Call for papers for the 2025 BabyLM workshop

TL;DR

The 2025 BabyLM workshop promotes research on data-efficient language modeling, cognitive plausibility, and interactive learning, encouraging submissions for a new INTERACTION track and a competition to advance understanding of language learning processes.

Contribution

This call introduces a new INTERACTION track focusing on interactive learning and expands the scope of the BabyLM competition to include diverse research areas.

Findings

New INTERACTION track promotes interactive language learning research

Expansion of competition to include cognitive plausibility and efficiency

Encourages interdisciplinary submissions in language modeling

Abstract

BabyLM aims to dissolve the boundaries between cognitive modeling and language modeling. We call for both workshop papers and for researchers to join the 3rd BabyLM competition. As in previous years, we call for participants in the data-efficient pretraining challenge in the general track. This year, we also offer a new track: INTERACTION. This new track encourages interactive behavior, learning from a teacher, and adapting the teaching material to the student. We also call for papers outside the competition in any relevant areas. These include training efficiency, cognitively plausible research, weak model evaluation, and more.