@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://aclanthology.org/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)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2026-teleai">
<titleInfo>
<title>TeleAI at SemEval-2026 Task 6: A Confidence-Aware Multi-Stage Reasoning Framework with Chain-of-Thought</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lingling</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoyu</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiquan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fang</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuangyong</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuelong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<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).</abstract>
<identifier type="citekey">shi-etal-2026-teleai</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.206/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1591</start>
<end>1609</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TeleAI at SemEval-2026 Task 6: A Confidence-Aware Multi-Stage Reasoning Framework with Chain-of-Thought
%A Shi, Lingling
%A Jin, Haoyu
%A Wang, Shiquan
%A Yu, Fang
%A Song, Shuangyong
%A Li, Xuelong
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F shi-etal-2026-teleai
%X 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).
%U https://aclanthology.org/2026.semeval-1.206/
%P 1591-1609
Markdown (Informal)
[TeleAI at SemEval-2026 Task 6: A Confidence-Aware Multi-Stage Reasoning Framework with Chain-of-Thought](https://aclanthology.org/2026.semeval-1.206/) (Shi et al., SemEval 2026)
ACL