Vaccine-critical memes have emerged as a growing challenge for public health communication, combining images and text to spread misinformation in ways that are difficult to detect automatically. In this paper, we have described our system for the EEUCA 2026 Shared Task on Multimodal Vaccine-Critical Meme Detection, classifying memes from the VaxMeme dataset into Vaccine-Critical, Neutral and Pro-Vaccine categories. We have experimented with multiple text encoders and visual backbones, finding that Twitter-RoBERTa fused with CLIP ViT-L/14 through gated cross-modal attention has achieved a test macro F1 of 0.8357. We have further shown that domain-specific pretraining has outperformed larger general-purpose models, highlighting the importance of domain adaptation over raw model scale. Finally, our system has secured the 3rd position on the shared task leaderboard.

Hope speech has played a vital role in online communities, yet most NLP work has focused on English and a few high-resource languages, leaving code-mixed varieties like Tulu largely unexplored. In the Shared Task on Hope Speech Detection in Code-Mixed Tulu at DravidianLangTech@ACL 2026, we have tackled two subtasks: (i) coarse-grained classification into Encouraging, Discouraging, Uninvolved and Blended categories (Task 1) and (ii) fine-grained classification into Optimistic, Realistic, Inspiring, Fading and Hopelessness (Task 2).We have fine-tuned three multilingual transformer encoders XLM-RoBERTa-base, MuRIL and mBERT on the official training splits. In Task 1, a three-way soft-voting ensemble of all three models has yielded the best performance with a macro F1 of 0.58, securing 1st place. In Task 2, XLM-RoBERTa-base alone has outperformed both MuRIL and mBERT, achieving a macro F1 of 0.42 and also securing 1st place.

Abusive language targeting women has been a serious problem on Tamil social media and building systems to detect it automatically is harder than it looks. Tamil is morphologically complex, people have written it mixed with English in ways no dictionary has accounted for and a lot of the hostility has been indirect enough that has slipped past models trained on surface patterns. In the Shared Task on Abusive Tamil Text Targeting Women on Social Media DravidianLangTech@ACL 2026, we have worked on classifying Tamil YouTube comments as Abusive or Non-Abusive. We have trained three transformer models four times each with different learning rates, giving us 12 models total. Their predicted probabilities have been averaged to make the final decision. The 12-model ensemble has achieved a macro F1 of 0.8086, outperforming all individual models and securing 4th place in the shared task. Combining Tamil-specialized and multilingual transformer models has outperformed any single-architecture approach.

Visual hallucination detection in culturally grounded images has remained challenging due to fine-grained visual distinctions and knowledge-dependent statements. In the ImageEval2026 / ArabicNLP26 AynVQA Shared Task, we have participated in Task 1b by developing a system based on Qwen2.5-VL-7B Instruct with 4-bit quantization. We have reformulated hallucination detection as a single choice selection problem to enforce the exactly one-correct-statement constraint and have introduced confidence-based selective refinement using paraphrase ensemble voting. Our final system has achieved 0.942 accuracy, 0.058 CI, 0.000 CFHR,0.942 Q+accuracy and 0.971 Q−accuracy, ranking 6th in the English track. Error analysis has revealed that the remaining failures have mostly stemmed from fine-grained cultural and visual grounding challenges rather than prediction inconsistency.

Arabic harmful-prompt detection has remained challenging due to dialectal variation, implicit expressions and context-dependent intent. In the ArGuard 2026 Shared Task, we have participated in Subtask B1, a binary safe/unsafe classification task scored by macro-F1. We have identified evaluation leakage in an initial pipeline: the development set has been reused for early stopping, threshold tuning and ensemble optimization, which has inflated development scores while masking poor generalization on the blind test set. To correct this, we have introduced a leakage-controlled protocol with separate fitting, checkpoint-selection and tuning splits and have compared a TF-IDF SVM baseline, MARBERTv2 and a stacking ensemble, selecting the best-performing method based on tuning-set results. We have further applied five rounds of error-driven data augmentation to address recurring failure patterns. Our final system has achieved 0.861 accuracy, 0.878 precision, 0.862 recall and 0.860 macro-F1 on the blind test leaderboard, ranking 5th. Manual error analysis has shown that remaining errors have mainly stemmed from false positives on sensitive but non-harmful content, confirming that leakage-controlled evaluation has been necessary for a reliable blind-test estimate.

Readability assessment has played a vital role in education, yet most NLP work has focused on English and a few high-resource languages, leaving fine-grained Arabic readability comparatively unexplored. In the BAREC Shared Task 2026, we have addressed sentence-level classification into 19 ordinal readability levels under the Strict Track, fine-tuning four Arabic transformer encoders, MARBERT, CAMeLBERT MSA, AraELECTRA and AraBERTv2, on the official training split under multiple ordinal-aware losses: soft cross-entropy, squared Earth Mover’s Distance, direct ordinal regression and a CORAL-style cumulative-threshold loss. A validation-only greedy ensemble of all resulting models, combined with a learned per-level threshold post-processing step, has raised performance from a best single-model QWK of 0.8341 to a final validation QWK of 0.8507. On the official Blind Test leaderboard, our system has achieved a QWK of 0.848, securing 3rd place in the Strict Track