用双模型集成与复杂度门控提升政治回应模糊性检测准确率
CSE-UOI at SemEval-2026 Task 6: A Two-Stage Heterogeneous Ensemble with Deliberative Complexity Gating for Political Evasion Detection
- 采用双大模型自一致性与加权投票的异构集成方法
- 通过响应长度代理实现模糊性判别，达0.85宏平均F1
- 适合关注政治话语分析与模型推理机制的研究者
本文介绍我们在SemEval-2026任务6中的系统，该任务将政治访谈回应的清晰度分为三类：明确回答、模棱两可和明确回避。我们提出一种基于自一致性（SC）和加权投票的异构双大语言模型（LLM）集成方法，并引入一种新型后处理修正机制——思辨复杂度门控（DCG）。该机制利用跨模型行为信号，发现响应长度代理与样本模糊性存在强相关性。为进一步探究提升模糊性检测的机制，我们评估了多智能体辩论作为增强思辨能力的替代策略。与依赖跨模型行为信号动态调控推理的DCG不同，辩论通过增加智能体数量但不提升模型多样性来增强推理。我们的方案在测试集上取得0.85的宏平均F1分数，获得第三名，与第二名报告得分并列。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。