@inproceedings{tankala-etal-2025-curll,
    title = "{C}ur{LL}: A Developmental Framework to Evaluate Continual Learning in Language Models",
    author = "Tankala, Pavan Kalyan  and
      Mishra, Shubhra  and
      Lokam, Satya  and
      Goyal, Navin",
    editor = "Charpentier, Lucas  and
      Choshen, Leshem  and
      Cotterell, Ryan  and
      Gul, Mustafa Omer  and
      Hu, Michael Y.  and
      Liu, Jing  and
      Jumelet, Jaap  and
      Linzen, Tal  and
      Mueller, Aaron  and
      Ross, Candace  and
      Shah, Raj Sanjay  and
      Warstadt, Alex  and
      Wilcox, Ethan Gotlieb  and
      Williams, Adina",
    booktitle = "Proceedings of the First BabyLM Workshop",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.babylm-main.20/",
    pages = "256--278",
    ISBN = "TODO",
    abstract = "We introduce a comprehensive continual learning dataset and benchmark CurLL grounded in human developmental trajectories from ages 5{--}10, enabling systematic and fine-grained assessment of models' ability to progressively acquire new skills. CurLL spans five developmental stages (0{--}4) covering ages 5{--}10, with a skill graph of 32 high-level skills, 128 sub-skills, 350+ goals, and 1,300+ indicators explicitly modeling prerequisite relationships. We generate a 23.4B-token synthetic dataset with controlled skill progression, vocabulary complexity, and format diversity, comprising paragraphs, comprehension-based QA (CQA), skill-testing QA (CSQA), and instruction{--}response (IR) pairs. Stage-wise token counts range from 2.12B to 6.78B tokens, supporting precise analysis of forgetting, forward transfer, and backward transfer. Using a 135M-parameter transformer trained under independent, joint, and sequential (continual) setups, we show trade-offs in skill retention and transfer efficiency. By mirroring human learning patterns and providing fine-grained control over skill dependencies, this work advances continual learning evaluations for language models."
}