@inproceedings{vladislav-etal-2026-unveiling,
    title = "Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story",
    author = "Vladislav, Pedashenko  and
      Kushnareva, Laida  and
      Nibal, Yana Khassan  and
      Tulchinskii, Eduard  and
      Kuznetsov, Kristian  and
      Zharchinskii, Vladislav  and
      Maximov, Yury  and
      Piontkovskaya, Irina",
    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.370/",
    pages = "7916--7944",
    ISBN = "979-8-89176-380-7",
    abstract = "Intrinsic dimension (ID) is an important tool in modern LLM analysis, informing studies of training dynamics, scaling behavior, and dataset structure, yet its textual determinants remain underexplored. We provide the first comprehensive study grounding ID in interpretable text properties through cross-encoder analysis, linguistic features, and sparse autoencoders (SAEs). In this work, we establish three key findings. First, ID is complementary to entropy-based metrics: after controlling for length, the two are uncorrelated, with ID capturing geometric complexity orthogonal to prediction quality. Second, ID exhibits robust genre stratification: scientific prose shows low ID ($\sim 8$), encyclopedic content medium ID ($\sim 9$), and creative/opinion writing high ID ($\sim 10.5$) across all models tested. This reveals that contemporary LLMs find scientific text ``representationally simple'' while fiction requires additional degrees of freedom. Third, using SAEs, we identify causal features: scientific signals (formal tone, report templates, statistics) reduce ID; humanized signals (personalization, emotion, narrative) increase it. Steering experiments confirm these effects are causal. Thus, for contemporary models, scientific writing appears comparatively ``easy'', whereas fiction, opinion, and affect add representational degrees of freedom. Our multi-faceted analysis provides practical guidance for the proper use of ID and the sound interpretation of ID-based results."
}