# KCLarity at SemEval-2026 Task 6: Encoder and Zero-Shot Approaches to Political Evasion Detection

arXiv: https://arxiv.org/abs/2603.06552 · HTML: https://mlsanity.com/paper/2603.06552/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 30 references that are in the map.
- First posted on arXiv 6 Mar 2026.

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

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)](https://mlsanity.com/paper/2003.12206/) (2020)
- [When the Majority is Wrong: Modeling Annotator Disagreement for Subjective Tasks](https://mlsanity.com/paper/2305.06626/) (2023)
- [Reproducibility in Machine Learning-based Research: Overview, Barriers and Drivers](https://mlsanity.com/paper/2406.14325/) (2024)
- [A Survey of Cognitive Distortion Detection and Classification in NLP](https://mlsanity.com/paper/2508.09878/) (2025)

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

- [A Shaky Voice Is Not Always a Dodge: Benchmarking Textual and Vocal Evasion Detection in Earnings Calls](https://mlsanity.com/paper/2608.28040/) (2026)

## Abstract (arXiv)

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.