@inproceedings{barbenel-etal-2026-l1,
    title = "{L}1 Influence in {L}2 Language Models: A Human-centric Approach",
    author = "Barbenel, Laura  and
      Goulder, Lily  and
      O{'}Driscoll, Aoife  and
      Salhan, Suchir  and
      Arnett, Catherine  and
      Caines, Andrew  and
      Buttery, Paula",
    editor = "Ma, Martin Ziqiao  and
      Liu, Emmy  and
      Liu, Jing  and
      Chang, Tyler A.  and
      Fourtassi, Abdellah  and
      Warstadt, Alex  and
      Hahn, Michael  and
      Sun, Weiwei  and
      Shi, Freda",
    booktitle = "Proceedings of the 1st Workshop on Computational Developmental Linguistics ({CDL})",
    month = jul,
    year = "2026",
    address = "Grand Hyatt Manchester San Diego, 1 Market Pl, San Diego, CA 92101",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.cdl-1.15/",
    pages = "92--116",
    ISBN = "979-8-89176-428-6",
    abstract = "Language learners typically exhibit first language (L1) influence in their written second language (L2) production. We investigate whether similar patterns emerge in L2 language models (L2LMs), which are typically assessed on task-based benchmarks rather than on language use. We evaluate the use of Native Language Identification (NLI) as a method for detecting whether L2LMs exhibit human-like L1 influence. Using existing learner corpora and our novel L2 English dataset, we identify the conditions that yield the highest NLI accuracy, and show that text length but not proficiency affects performance. We then apply NLI to L2LM-generated text under various instruction-tuning and prompting conditions. We find that instruction tuning on human learner essays yields high NLI accuracy ({\textasciitilde}90{\%}) and is necessary for detectable L1 influence. Whilst NLI accuracy is similar for L2LM and human essays, human evaluation shows that LM-generated L1 influence remains distinguishable from human writing."
}