[Call for Papers] The 2nd BabyLM Challenge: Sample-efficient pretraining on a developmentally plausible corpus

TL;DR

The 2nd BabyLM Challenge aims to promote sample-efficient pretraining on developmentally plausible corpora, introducing new rules, a paper track, and multimodal data to advance language model research.

Contribution

This paper announces the second BabyLM Challenge with updated rules, a new paper track, and multimodal data, encouraging diverse and cognitively-inspired approaches to language model pretraining.

Findings

Introduction of a paper track for diverse submissions

Relaxed data construction rules within 100M/10M words

Provision of multimodal vision-and-language dataset

Abstract

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.