@inproceedings{roscan-nisioi-2026-archaeology,
    title = "Archaeology at {WE}-2026 {PARSEME} 2.0 Subtask 1 and 2: Parsing is for Encoders, Paraphrasing is for {LLM}s",
    author = "Roscan, Rares-Alexandru  and
      Nisioi, Sergiu",
    editor = {Ojha, Atul Kr.  and
      Mititelu, Verginica Barbu  and
      Constant, Mathieu  and
      Stoyanova, Ivelina  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Rademaker, Alexandre},
    booktitle = "Proceedings of the 22nd Workshop on Multiword Expressions ({MWE} 2026)",
    month = mar,
    year = "2026",
    address = "Rabat, Marocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.mwe-1.31/",
    pages = "237--247",
    ISBN = "979-8-89176-363-0",
    abstract = "This paper presents our approach to the PARSEME 2.0 Shared Task on Romanian, covering both Identification (Subtask 1) and Paraphrasing (Subtask 2). While Large Language Models (LLMs) excel at semantic generation, we hypothesize that they lack the structural precision required for MWE identification, leading to ``boundary hallucinations'' that compromise downstream simplification. Our Rank 1 results on Romanian confirm this: a specialized encoder (RoBERT) using standard sequence labeling outperforms both few-shot LLMs and complex structural parsers (MTLB-STRUCT). This justifies our proposed pipeline: using encoders as precise ``pointers'' to guide the generative power of LLMs."
}