@inproceedings{korner-etal-2026-meanings,
    title = "When Meanings Meet: Investigating the Emergence and Quality of Shared Concept Spaces during Multilingual Language Model Training",
    author = {K{\"o}rner, Felicia  and
      M{\"u}ller-Eberstein, Max  and
      Korhonen, Anna  and
      Plank, Barbara},
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-long.145/",
    pages = "3149--3169",
    ISBN = "979-8-89176-380-7",
    abstract = "Training Large Language Models (LLMs) with high multilingual coverage is becoming increasingly important {---} especially when monolingual resources are scarce. Recent studies have found that LLMs process multilingual inputs in shared concept spaces, thought to support generalization and cross-lingual transfer. However, these prior studies often do not use causal methods, lack deeper error analysis or focus on the final model only, leaving open how these spaces emerge *during training*. We investigate the development of language-agnostic concept spaces during pretraining of EuroLLM through the causal interpretability method of activation patching. We isolate cross-lingual concept representations, then inject them into a translation prompt to investigate how consistently translations can be altered, independently of the language. We find that *shared concept spaces emerge early and continue to refine*, but that *alignment with them is language-dependent*. Furthermore, in contrast to prior work, our fine-grained manual analysis reveals that some apparent gains in translation quality reflect shifts in behavior {---} like selecting senses for polysemous words or translating instead of copying cross-lingual homographs {---} rather than improved translation ability. Our findings offer new insight into the training dynamics of cross-lingual alignment and the conditions under which causal interpretability methods offer meaningful insights in multilingual contexts."
}