发表机构
Kaons 𝑲 ∗（Kaons 𝑲 ∗）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对政治逃避检测难题，提出AsymVerify系统用于SemEval-2026任务6的三元分类。核心方法是对问答对分类后对低置信预测进行非对称验证，主要贡献是取得高排名，在不同数据集上提升宏F1分数，且降低推理成本。
AI 中文摘要
政治逃避难以检测，因为逃避性回答往往看似合作却避免具体承诺。我们提出了AsymVerify，这是一个用于SemEval-2026任务6的置信门控验证系统，该任务对明确回复、矛盾和明确无回复进行三元分类。AsymVerify在评估集（D_eval，n = 237）上的宏F1分数为0.85，在官方排行榜的41支队伍中排名第二。该系统先对每个问答对进行分类，然后对低置信度预测选择性地应用降级验证（CR/CNR -> AMB）或升级验证（AMB -> CR）。开发分析表明错误集中在矛盾边界的两个方向，这促使了这种非对称双验证器设计，同时置信门控使额外推理成本较低。在D_dev（n = 308）上，使用GLM-4.7的AsymVerify在每次示例1.48次调用时比单遍分类获得了+17.1的宏F1，仅升级验证器就在D_dev上使每个测试的LLM后端比其单遍基线提高了+6.8到+15.2的宏F1。代码可在这个https URL获取。
英文摘要
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 (D_eval, 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 -> AMB) or upgrade verification (AMB -> 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 D_dev (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 D_dev by +6.8 to +15.2 Macro F1 over its single-pass baseline. Code is available at https://github.com/kaons-research/AsymVerify-ACL.
CommentsAccepted to SemEval-2026 Task 6 (CLARITY) at ACL 2026. Team AsymVerify placed 2nd of 41 teams on the official Subtask 1 leaderboard. Task: https://konstantinosftw.github.io/CLARITY-SemEval-2026/. Code: https://github.com/kaons-research/AsymVerify-ACL. Website: https://kaons.com/
