# Knowledge Visualization: A Benchmark and Method for Knowledge-Intensive Text-to-Image Generation Source: [Knowledge Visualization: A Benchmark and Method for Knowledge-Intensive Text-to-Image Generation]() Collection index: [llms.txt]() Data updated: 2026-04-28T05:00:04.744Z Authors: Ran Zhao, Sheng Jin, Size Wu, Kang Liao, Zerui Gong, Zujin Guo, Yang Xiao, Wei Li Published: 2026-04-24T07:33:52.000Z ## Abstract Recent text-to-image (T2I) models have demonstrated impressive capabilities in photorealistic synthesis and instruction following. However, their reliability in knowledge-intensive settings remains largely unexplored. Unlike natural image generation, knowledge visualization requires not only semantic alignment but also strict adherence to domain knowledge, structural constraints, and symbolic conventions, exposing a critical gap between visual plausibility and scientific correctness. To systematically study this problem, we introduce KVBench, a curriculum-grounded benchmark for evaluating knowledge-intensive T2I generation. KVBench covers six senior high-school subjects: Biology, Chemistry, Geography, History, Mathematics, and Physics. The benchmark consists of 1,800 expert-curated prompts derived from over 30 authoritative textbooks. Using this benchmark, we evaluate 14 state-of-the-art open- and closed-source models, revealing substantial deficiencies in logical reasoning, symbolic precision, and multilingual robustness, with open-source models consistently underperforming proprietary systems. To address these limitations, we further propose KE-Check, a two-stage framework that improves scientific fidelity via (1) Knowledge Elaboration for structured prompt enrichment, and (2) Checklist-Guided Refinement for explicit constraint enforcement through violation identification and constraint-guided editing. KE-Check effectively mitigates scientific hallucinations, narrowing the performance gap between open-source and leading closed-source models. Data and codes are publicly available at https://github.com/zhaoran66/KVBench. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Knowledge Visualization on KVBench Brief Caption](): Knowledge Visualization; KVBench Brief Caption; Overall Score (zh): 47.67. - [Detailed Caption on KVBench Detailed Caption, zh](): Detailed Caption; KVBench Detailed Caption, zh; Overall Score: not recorded. - [Detailed Caption on KVBench Detailed Caption en](): Detailed Caption; KVBench Detailed Caption en; Overall Score: not recorded. ## Original sources and implementation [Original paper]() [PDF]()