AsymVerify at SemEval-2026 Task 6: Asymmetric Confidence-Gated Verification for Political Evasion Detection

AsymVerify, a confidence-gated verification system for political evasion detection, scored 0.85 Macro F1 on the evaluation split (D_eval, n=237), placing 2nd out of 41 teams at SemEval-2026 Task 6. The system, developed by researchers, uses asymmetric two-verifier design to handle Ambivalent boundary errors, achieving +17.1 Macro F1 over single-pass classification on D_dev (n=308) with GLM-4.7 at 1.48 calls/example.

arXiv:2607.20439v1 Announce Type: new 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 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.