# CSE-UOI at SemEval-2026 Task 6: A Two-Stage Heterogeneous Ensemble with Deliberative Complexity Gating for Political Evasion Detection

arXiv: https://arxiv.org/abs/2603.12453 · HTML: https://mlsanity.com/paper/2603.12453/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 21 references that are in the map.
- First posted on arXiv 12 Mar 2026.

## Builds on (most cited first, 8 of 8)

- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding](https://mlsanity.com/paper/2310.05424/) (2023)
- [Multi-Agent Debate for LLM Judges with Adaptive Stability Detection](https://mlsanity.com/paper/2510.12697/) (2025)
- [The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs](https://mlsanity.com/paper/2508.08285/) (2025)
- ["I Never Said That": A dataset, taxonomy and baselines on response clarity classification](https://mlsanity.com/paper/2409.13879/) (2024)
- [How Does Response Length Affect Long-Form Factuality](https://mlsanity.com/paper/2505.23295/) (2025)
- [MSA at BEA 2025 Shared Task: Disagreement-Aware Instruction Tuning for Multi-Dimensional Evaluation of LLMs as Math Tutors](https://mlsanity.com/paper/2505.18549/) (2025)

## Built on by (most cited first, 1 of 1)

- [SemEval-2026 Task 6: CLARITY -- Unmasking Political Question Evasions](https://mlsanity.com/paper/2603.14027/) (2026)

## Abstract (arXiv)

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.