KCLarity at SemEval-2026 Task 6: Encoder and Zero-Shot Approaches to Political Evasion Detection
This work addresses the problem of classifying ambiguity and evasion in political discourse for researchers in natural language processing, providing competitive results on a new benchmark.
This paper explores two modeling approaches for detecting political evasion: direct clarity prediction and evasion prediction with hierarchical derivation. RoBERTa-large performed best on the public test set, while zero-shot GPT-5.2 showed better generalization on the hidden evaluation set.
This paper describes the KCLarity team's participation in CLARITY, a shared task at SemEval 2026 on classifying ambiguity and evasion techniques in political discourse. We investigate two modelling formulations: (i) directly predicting the clarity label, and (ii) predicting the evasion label and deriving clarity through the task taxonomy hierarchy. We further explore several auxiliary training variants and evaluate decoder-only models in a zero-shot setting under the evasion-first formulation. Overall, the two formulations yield comparable performance. Among encoder-based models, RoBERTa-large achieves the strongest results on the public test set, while zero-shot GPT-5.2 generalises better on the hidden evaluation set.