TTLab at StanceEval-2026: A Cloze-Style Prompting Approach for Arabic-Language Stance Detection (CLASP-Ar)

arXiv:2609.29733 · cs.CL, cs.LG · Submitted 2026-09-24 · Read on arXiv

cs.CL, cs.LG

Submitted: 2026-09-24

Updated: 2026-09-24

Comments: Accepted at ArabicNLP 2026 StanceEval-2026 shared task

License: http://creativecommons.org/licenses/by/4.0/

The gist: Arabic-language stance detection remains challenging, and previous shared-task systems have largely relied on multitask learning and ensembles.

Terminology

Abstract

Arabic-language stance detection remains challenging, and previous shared-task systems have largely relied on multitask learning and ensembles. While these systems achieve state-of-the-art performance, their applicability and transferability are limited by the additional complexity introduced by multitask learning.To reduce this complexity, we introduce CLASP-Ar, which reformulates the task as cloze-style masked language modeling. In this approach, the target, predicted sentiment, and text are combined into a single prompt whose[MASK] prediction is restricted to a verbalizer-constrained label vocabulary.

Sources

Related papers