NarSiL at SemEval-2026 Task 4: A Multi-Expert, Multi-Pathway System for Narrative Story Similarity

HausaNLP at SemEval-2026 Task 7: A Locale-Conditional, Multi-Model Prompting Pipeline for Hausa Cultural Question Answering

Error analysis shows that a non-trivial fraction of failures are placeholder strings caused by API errors rather than incorrect generations, and that surface-level mismatches (verbosity, ortho-graphic variation) account for many of the remaining errors.

Team hugang11 at SemEval-2026 Task 1: A CoT-SFT, Teacher-Constructed DPO, and Deterministic Post-processing Pipeline for Chinese Humor Generation

The hugang11 system addresses a practical trade-off in creative text generation: models that produce sharper and more stylized jokes often become less stable in output format, and builds a three-stage pipeline that combines chain-of-thought-augmented supervised fine-tuning (CoT-SFT), teacher-constructed direct preference optimization (DPO), and deterministic post-processing.

GUNLP at SemEval-2026 Task 10: Emotion-Aware Multi-Task Learning for Conspiracy Detection

ILA-POLAR at SemEval-2026 Task 9: Multi-label Polarization Classification with TwHIN-BERT and SCUT Threshold Optimization

RAG Pipeline Strategies for Ukrainian Multi-Domain Document Understanding Task

LLM-Assisted Sentiment Analysis for Indonesia's Coretax Policy: A Knowledge Distillation and Human-in-the-Loop Approach

The lack of high-quality labeled datasets remains a major challenge for sentiment analysis in low-resource languages such as Indonesian, particularly in specialized domains like fiscal policy. This study investigates the effectiveness of Large Language Models (LLMs) as automated annotators within a teacher-student knowledge distillation framework. Using social media data from X related to Indonesia's Coretax system, three training scenarios were evaluated: AI-labeled data, human-labeled data, and a hybrid approach. The results show that GPT-4o achieves substantial agreement with human annotators, with a Cohen's Kappa score of 0.61. Furthermore, the student model IndoBERT trained on the combined dataset outperforms other configurations, achieving a Macro F1-score of 0.64 and a Macro ROC-AUC of 0.84. These findings indicate that while LLMs cannot fully replace human judgment, they significantly enhance scalability and enable near real-time policy evaluation in low-resource settings through effective human-AI collaboration.