@inproceedings{zhou-etal-2026-matters,
    title = "What Matters to an {LLM}? Behavioral and Computational Evidences from Summarization",
    author = "Zhou, Yongxin  and
      Wu, Changshun  and
      Mulhem, Philippe  and
      Schwab, Didier  and
      Peyrard, Maxime",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.findings-eacl.302/",
    pages = "5712--5737",
    ISBN = "979-8-89176-386-9",
    abstract = "Large Language Models (LLMs) are now state-of-the-art at summarization, yet the internal notion of importance that drives their information selections remains hidden. We propose to investigate this by combining behavioral and computational analyses. Behaviorally, we generate a series of length-controlled summaries for each document and derive empirical importance distributions based on how often each information unit is selected. These reveal that LLMs converge on consistent importance patterns, sharply different from pre-LLM baselines, and that LLMs cluster more by family than by size. Computationally, we identify that certain attention heads align well with empirical importance distributions, and that middle-to-late layers are strongly predictive of importance. Together, these results provide initial insights into *what* LLMs prioritize in summarization and *how* this priority is internally represented, opening a path toward interpreting and ultimately controlling information selection in these models."
}