Jul 2026
The First ChineseBabyLM Challenge: training data-efficient and cognitively plausible language models for Chinese
The first ChineseBabyLM Challenge, organized as part of NLPCC 2026, asked participants to train language models from scratch using no more than 102M Chinese words and provides a benchmark for advancing data-efficient and cognitively plausible approaches to Chinese language modeling.
Siyuan Song, Zhiheng Qian, Yun-Hao Zhang et al.
· arXiv.org · 0 citations