@inproceedings{shi-etal-2026-teleai,
    title = "{T}ele{AI} at {S}em{E}val-2026 Task 6: A Confidence-Aware Multi-Stage Reasoning Framework with Chain-of-Thought",
    author = "Shi, Lingling  and
      Jin, Haoyu  and
      Wang, Shiquan  and
      Yu, Fang  and
      Song, Shuangyong  and
      Li, Xuelong",
    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-1.206/",
    pages = "1591--1609",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper describes our framework for SemEval-2026 Task 6 (CLARITY - Unmasking Political Question Evasions), which focuses on classifying clarity and fine-grained evasion types in political question-answering dialogues. We propose CAMSR-CoT, a confidence-aware multi-stage reasoning framework that unifies the two subtasks through hierarchical label modeling. The framework adopts a confidence-based routing strategy: high-certainty cases are directly resolved, while ambiguous samples are routed to deeper Chain-of-Thought reasoning stages with boundary-aware few-shot exemplars to mitigate label confusion. On the development set, our framework achieves Macro-F1 scores of 0.812 on SubTask 1 and 0.617 on SubTask 2. On the official hidden test set, it ranks 1st in both SubTask 1 (Macro-F1 = 0.89) and SubTask 2 (Macro-F1 = 0.68)."
}