CSE-UOI在SemEval-2026任务6中的表现：一种双阶段异构集成与 deliberative 复杂性门控的政治理论逃避检测方法
CSE-UOI at SemEval-2026 Task 6: A Two-Stage Heterogeneous Ensemble with Deliberative Complexity Gating for Political Evasion Detection
AI总结：
本文提出一种双阶段异构集成方法，结合自我一致性与加权投票，以及新颖的后处理修正机制Deliberative Complexity Gating，用于政治逃避检测，最终在评估集上获得0.85的Macro-F1分数。
摘要：
本文描述了我们在SemEval-2026任务6中的系统，该系统将政治访谈中的回应清晰度分为三个类别：清晰回复、矛盾回复和清晰非回复。我们提出了一种异构双大型语言模型（LLM）集成方法，结合自我一致性（SC）和加权投票，并提出了一种新的后处理修正机制，即Deliberative Complexity Gating（DCG）。该机制利用跨模型行为信号，并利用发现LLM响应长度代理与样本模糊性之间存在强相关性的发现。为了进一步研究提高模糊性检测的机制，我们评估了多代理辩论作为增加 deliberative 能力的替代策略。与DCG不同，后者通过跨模型行为信号自适应地门控推理，而辩论则通过增加代理数量而不增加模型多样性。我们的解决方案在评估集上获得了0.85的Macro-F1分数，取得了第三名，并与第二好的报告分数并列。
英文摘要：
This paper describes our system for SemEval-2026 Task 6, which classifies clarity of responses in political interviews into three categories: Clear Reply, Ambivalent, and Clear Non-Reply. We propose a heterogeneous dual large language model (LLM) ensemble via self-consistency (SC) and weighted voting, and a novel post-hoc correction mechanism, Deliberative Complexity Gating (DCG). This mechanism uses cross-model behavioral signals and exploits the finding that an LLM response-length proxy correlates strongly with sample ambiguity. To further examine mechanisms for improving ambiguity detection, we evaluated multi-agent debate as an alternative strategy for increasing deliberative capacity. Unlike DCG, which adaptively gates reasoning using cross-model behavioral signals, debate increases agent count without increasing model diversity. Our solution achieved a Macro-F1 score of 0.85 on the evaluation set, securing 3rd place and tied with the second-best reported score.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
