This paper presents the IReL_IIT(BHU) submission to SemEval-2026 Task 9 for the Chinese language track. We participated in all three subtasks: binary polarization detection,multi-label polarization type classification, and multi-label manifestation identification. Our approach is based on a unified transformer based framework with cross-validation, prediction aggregation, and threshold optimization to improve robustness across tasks. On the official evaluation, our systems achieved Macro-F1 scores of 0.9081, 0.7962, and 0.6484 for Subtasks 1, 2, and 3, respectively on test data.

This paper presents our submissions to the LT-EDI@ACL 2026 Shared Task on Gender Inclusive Language Generation. The task focuses on controlled text rewriting that reduces gender bias while keeping the original meaning and fluency intact. We participated in boththe subtasks and treated them independently, training separate instances of the instruction-tuned encoder–decoder model on the respective training datasets. Scores are calculated based on averages across different rubrics, including Gender Assumption (GA), Gender Neutrality (GN), and Quality Relevance (QR) for Task A, and Politeness and Respectful (PR), Contextual Counter-Narrative Coherence (CCNC), and Quality and Relevance (QR) for Task B.For Subtask A (Gender-Inclusive Language Generation) in the English dataset, an average score of 43.7917 could be achieved. For Subtask B (Counterfactual Generation), we achieved an average score of 82.6241. Overall, the experiments indicate that full finetuning of instruction-tuned transformers provides an effective way to produce sentence in gender-neutral form and also producing counter-factual sentences for biased one, wheneach subtask is optimized on its own data.

Recent advances in text-to-image generation have enabled automated visual storytelling, yet most existing datasets remain monolingual and culturally narrow. We introduce MUSIA, a Multilingual Story Illustration Corpus designed to advance research in cross-lingual and culturally grounded narrative illustration. MUSIA comprises bilingual (English-Hindi) story-image pairs drawn from open literary and folk sources, curated to reflect diverse cultural themes, artistic styles, and linguistic structures. Each story includes multiple illustrations aligned at the scene level, accompanied by quality-verified mappings for narrative-visual coherence. To establish a reproducible benchmark, we propose a two-stage baseline combining transformer-based semantic summarization with diffusion-based image generation, achieving strong performance in relevance, visual quality, and consistency. MUSIA represents the first step toward a scalable, culturally inclusive benchmark for multilingual visual storytelling, enabling fair and reproducible research across low-resource and underrepresented languages.