CSE-UOI at SemEval-2026 Task 6: A Two-Stage Heterogeneous Ensemble with Deliberative Complexity Gating for Political Evasion Detection
This work addresses political evasion detection for natural language processing applications, but it is incremental as it builds on existing ensemble and LLM methods for a specific benchmark task.
The paper tackled the problem of classifying clarity in political interview responses into three categories by proposing a two-stage heterogeneous ensemble with a novel post-hoc correction mechanism called Deliberative Complexity Gating, achieving a Macro-F1 score of 0.85 and securing 3rd place in the competition.
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.