@inproceedings{kawada-2026-asymverify,
    title = "{A}sym{V}erify at {S}em{E}val-2026 Task 6: Asymmetric Confidence-Gated Verification for Political Evasion Detection",
    author = "Kawada, Sebastien",
    editor = "Kochmar, Ekaterina  and
      Ghosh, Debanjan  and
      North, Kai  and
      Komachi, Mamoru",
    booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.semeval-1.202/",
    pages = "1554--1567",
    ISBN = "979-8-89176-414-9",
    abstract = "Political evasion is difficult to detect because evasive answers often appear cooperative while avoiding concrete commitment. We present AsymVerify, a confidence-gated verification system for SemEval-2026 Task 6, a three-way classification of Clear Reply, Ambivalent, and Clear Non-Reply responses. AsymVerify scored 0.85 Macro F1 on the evaluation split (Deval, n=237), placing 2nd out of 41 teams on the official leaderboard. The system first classifies each question-answer pair, then selectively applies downgrade verification (CR/CNR {\textrightarrow} AMB) or upgrade verification (AMB {\textrightarrow} CR) to low-confidence predictions. Development analysis shows that errors concentrate at the Ambivalent boundary in both directions, motivating this asymmetric two-verifier design while confidence gating keeps additional inference cost low. On Ddev (n=308), AsymVerify with GLM-4.7 gains +17.1 Macro F1 over single-pass classification at 1.48 calls/example, and the upgrade verifier alone improves every tested LLM backend on Ddev by +6.8 to +15.2 Macro F1 over its single-pass baseline. Code is available at https://github.com/kaons-research/AsymVerify-ACL."
}