Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

BabyLM Turns 4 and Goes Multilingual: Call for Papers for the 2026 BabyLM Workshop

Leshem Choshen, Ryan Cotterell, Mustafa Omer Gul, Jaap Jumelet, Tal Linzen, Aaron Mueller, Suchir Salhan, Raj Sanjay Shah, Alex Warstadt, Ethan Gotlieb Wilcox

TL;DR

This work calls for both workshop papers and for researchers to join the 4th BabyLM competition, and offers a new track: Multilingual.

Abstract

The goal of the BabyLM is to stimulate new research connections between cognitive modeling and language model pretraining. We invite contributions in this vein to the BabyLM Workshop, which will also include the 4th iteration of the BabyLM Challenge. As in previous years, the challenge features two ``standard'' tracks (Strict and Strict-Small), in which participants must train language models on under 100M or 10M words of data, respectively. This year, we move beyond our previous English-only pretraining datasets with a new Multilingual track, focusing on English, Dutch, and Chinese. For the workshop, we call for papers related to the overall theme of BabyLM, which includes training efficiency, small-scale training datasets, cognitive modeling, model evaluation, and architecture innovation.

BabyLM Turns 4 and Goes Multilingual: Call for Papers for the 2026 BabyLM Workshop

TL;DR

This work calls for both workshop papers and for researchers to join the 4th BabyLM competition, and offers a new track: Multilingual.

Abstract

The goal of the BabyLM is to stimulate new research connections between cognitive modeling and language model pretraining. We invite contributions in this vein to the BabyLM Workshop, which will also include the 4th iteration of the BabyLM Challenge. As in previous years, the challenge features two ``standard'' tracks (Strict and Strict-Small), in which participants must train language models on under 100M or 10M words of data, respectively. This year, we move beyond our previous English-only pretraining datasets with a new Multilingual track, focusing on English, Dutch, and Chinese. For the workshop, we call for papers related to the overall theme of BabyLM, which includes training efficiency, small-scale training datasets, cognitive modeling, model evaluation, and architecture innovation.
Paper Structure (31 sections, 1 table)

This paper contains 31 sections, 1 table.

Table of Contents

  1. Introduction: BabyLM
  2. Key Dates
  3. Non-competition Workshop Submissions
  4. Topics
  5. Workshop Theme
  6. Paper submission
  7. Review & Publication
  8. Competition Details
  9. Track Rules
  10. New track: Multilingual
  11. Continuing Tracks
  12. Training Requirements
  13. Training Duration Limitations
  14. Intermediate Checkpoints
  15. Motivation
  16. ...and 16 more sections