@inproceedings{do-etal-2026-beyond,
    title = "Beyond Sampling: Self-Sorting for Long-Context Ranking",
    author = "Do, Juseon  and
      Han, Sungwoo  and
      Kwon, Jingun  and
      Kamigaito, Hidetaka  and
      Hayashi, Katsuhiko  and
      Watanabe, Taro",
    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.256/",
    pages = "4901--4910",
    ISBN = "979-8-89176-386-9",
    abstract = "Ranking is a fundamental component in a wide range of AI applications. However, large language models (LLMs) remain unstable on long-context ranking. Sliding-window processing is costly and listwise prompting over full candidates still yields inconsistent orders. We show that sampling alone, even with selection-based methods, cannot stabilize ranking because LLM consistency decomposes into within-list order and cross-list preference, in which a single stochastic process cannot align. To address this, we introduce Self-Sorting (SS), which generates m candidate lists and performs n selection-time re-rankings over those lists. SS fuses explicit within-list positions with implicit cross-list preferences to score entities and return a top-k set. Experimental results on five widely used ranking benchmarks show significant improvements in nDCG@{1,5,10}, highlighting the critical role of implicit consistency."
}