🧑🔬 Mehwish Nasim — papers of 2026 — Elamur Research2 papers · all years of Mehwish NasimConfident, Calibrated, or Complicit: Safety Alignment and Ideological Bias in LLM Hate Speech DetectionAnnual Meeting of the Association for Computational Linguistics (ACL)Sanjeevan Selvaganapathy, Mehwish Nasim2026NASIMLab at SemEval-2026 Task 9: A Comparative Analysis of Fine-Tuned Small Language Models vs. Generative Large Language Models for Multilingual Polarization Type DetectionInternational Workshop on Semantic Evaluation (SemEval)Neel Sabhahit, Sanjeevan Selvaganapathy, Mehwish Nasim2026This page in Markdown → https://md.research.elamur.ai/free/en/authors/mehwish-nasim/year/2026/