Answers are grounded in this paper and cite their sources.
Vision-language models (VLMs) increasingly support open-ended visual reasoning, yet their behavior in low-resource languages and sustainability-oriented domains remains underexplored. We introduce a controlled English–Bangla plastic-waste VQA benchmark comprising 402 image records derived from 136 base images and 2,412 question–answer pairs across five waste categories and three task types: recognition, visual description, and environmental reasoning. We evaluate GPT-4.1 mini, Gemini 2.5 Flash, Qwen2.5-VL-7B-Instruct, and Gemma-3-4B zero-shot using task-specific answer-quality metrics, bilingual consistency, and image ablation. Gemini 2.5 Flash yields the highest recognition point estimate, with 93.5% accuracy and 91.3% macro-F1. Across models, English normalized performance exceeds Bangla by 3.78 points on average, with the largest observed gap for environmental reasoning. Removing the image reduces normalized performance by 66.29 points for recognition, 52.89 for description, and 11.42 for environmental reasoning. The smaller environmental-reasoning ablation gap indicates that, in this benchmark, many environmental questions remain partly answerable from linguistic and domain priors. These results show why answer quality alone is insufficient for multilingual multimodal evaluation and motivate reporting cross-lingual consistency and sensitivity to visual evidence alongside conventional metrics.
No takes yet. Share an insight, caveat, or question.
Tarek Rahman (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: