Stochastic Gradient Descenders at SemEval-2026 Task 9: Few-Shot LLM Prompting for Polarization Type Classification
Year: 2026
Type: conference-paper
Abstract: This paper presents our system for SemEval-2026 Task 9 (POLAR), Subtask 2, which focuses on classifying polarization types in social media text.We investigate three paradigms: (i) fine-tuning mDeBERTa-v3 with domainadaptive pre-training, (ii) parameter-efficient adaptation of Qwen2.5-32B using LoRA, and (iii) few-shot prompting with Llama-3.3-70B-Instruct.Experimental results show that fewshot prompting, despite requiring no taskspecific training, outperforms both fine-tuning and parameter-efficient approaches.Notably, it achieves non-zero F1 scores across all polarization categories, which is critical under macroaveraged evaluation.Our system ranks 2nd out of 29 English submissions on the official leaderboard, achieving an F1 Macro of 0.5157.These findings highlight the effectiveness of large instruction-tuned models in low-resource, label-imbalanced classification settings.
Authors: Huynh Phu, Dang Thin
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166865338