@inproceedings{tran-tan-dinh-2026-ttda704,
title = "ttda704 at {S}em{E}val-2026 Task 6: Structured Chain-of-Thought Prompting for Political Evasion Detection",
author = "Tran Tan, Tai and
Dinh, An",
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-1.355/",
pages = "2817--2829",
ISBN = "979-8-89176-414-9",
abstract = "We present our system for SemEval-2026 Task 6 (CLARITY: Unmasking Political Question Evasions), which addresses political evasion detection in English question-answer pairs from U.S. presidential interviews.We compare two paradigms: (1) parameter-efficient fine-tuning of Qwen3 models (4B{--}32B) using QLoRA with tiered upsampling and weighted cross-entropy loss to address severe class imbalance, and (2) structured Chain-of-Thought (CoT) prompting with reasoning-capable API models, including DeepSeek-V3.2 and Grok-4-Fast.Our best system uses Grok-4-Fast with extended reasoning and few-shot hierarchical CoT prompting, achieving Macro F1 scores of 0.5147 on Subtask 2 (9-class evasion) and 0.7979 on Subtask 1 (3-class clarity). On the official leaderboard, it ranks 8/33 on Subtask 2 and 13/41 on Subtask 1. Ablation results show that hierarchical label presentation provides a useful reasoning scaffold and that extended reasoning helps models handle subtle pragmatic distinctions, although the strongest prompt variants are not statistically distinguishable in Macro F1."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tran-tan-dinh-2026-ttda704">
<titleInfo>
<title>ttda704 at SemEval-2026 Task 6: Structured Chain-of-Thought Prompting for Political Evasion Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tai</namePart>
<namePart type="family">Tran Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">An</namePart>
<namePart type="family">Dinh</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>We present our system for SemEval-2026 Task 6 (CLARITY: Unmasking Political Question Evasions), which addresses political evasion detection in English question-answer pairs from U.S. presidential interviews.We compare two paradigms: (1) parameter-efficient fine-tuning of Qwen3 models (4B–32B) using QLoRA with tiered upsampling and weighted cross-entropy loss to address severe class imbalance, and (2) structured Chain-of-Thought (CoT) prompting with reasoning-capable API models, including DeepSeek-V3.2 and Grok-4-Fast.Our best system uses Grok-4-Fast with extended reasoning and few-shot hierarchical CoT prompting, achieving Macro F1 scores of 0.5147 on Subtask 2 (9-class evasion) and 0.7979 on Subtask 1 (3-class clarity). On the official leaderboard, it ranks 8/33 on Subtask 2 and 13/41 on Subtask 1. Ablation results show that hierarchical label presentation provides a useful reasoning scaffold and that extended reasoning helps models handle subtle pragmatic distinctions, although the strongest prompt variants are not statistically distinguishable in Macro F1.</abstract>
<identifier type="citekey">tran-tan-dinh-2026-ttda704</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.355/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2817</start>
<end>2829</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ttda704 at SemEval-2026 Task 6: Structured Chain-of-Thought Prompting for Political Evasion Detection
%A Tran Tan, Tai
%A Dinh, An
%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 tran-tan-dinh-2026-ttda704
%X We present our system for SemEval-2026 Task 6 (CLARITY: Unmasking Political Question Evasions), which addresses political evasion detection in English question-answer pairs from U.S. presidential interviews.We compare two paradigms: (1) parameter-efficient fine-tuning of Qwen3 models (4B–32B) using QLoRA with tiered upsampling and weighted cross-entropy loss to address severe class imbalance, and (2) structured Chain-of-Thought (CoT) prompting with reasoning-capable API models, including DeepSeek-V3.2 and Grok-4-Fast.Our best system uses Grok-4-Fast with extended reasoning and few-shot hierarchical CoT prompting, achieving Macro F1 scores of 0.5147 on Subtask 2 (9-class evasion) and 0.7979 on Subtask 1 (3-class clarity). On the official leaderboard, it ranks 8/33 on Subtask 2 and 13/41 on Subtask 1. Ablation results show that hierarchical label presentation provides a useful reasoning scaffold and that extended reasoning helps models handle subtle pragmatic distinctions, although the strongest prompt variants are not statistically distinguishable in Macro F1.
%U https://aclanthology.org/2026.semeval-1.355/
%P 2817-2829
Markdown (Informal)
[ttda704 at SemEval-2026 Task 6: Structured Chain-of-Thought Prompting for Political Evasion Detection](https://aclanthology.org/2026.semeval-1.355/) (Tran Tan & Dinh, SemEval 2026)
ACL