@inproceedings{chen-etal-2026-emergence,
    title = "On the Emergence and Test-Time Use of Structural Information in Large Language Models",
    author = "Chen, Michelle Chao  and
      Miller, Moritz  and
      Sch{\textbackslash}{''}olkopf, Bernhard  and
      Guo, Siyuan",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.65/",
    pages = "1449--1465",
    ISBN = "979-8-89176-390-6",
    abstract = "Learning structural information from observational data is central to producing new knowledge outside the training corpus. This holds for mechanistic understanding in scientific discovery as well as flexible test-time compositional generation. We thus study how language models learn abstract structures and utilize the learnt structural information at test-time. To ensure a controlled setup, we design a natural language dataset based on linguistic structural transformations. We empirically show that the emergence of learning structural information correlates with complex reasoning tasks, and that the ability to perform test-time compositional generation remains limited."
}