IGenBench: New Benchmark Reveals Significant Reliability Issues in AI-Generated Infographics
Researchers have introduced IGenBench, the first benchmark for evaluating how reliably text-to-image models generate infographics, testing 10 state-of-the-art models across 600 curated cases and 30 infographic types. The study finds that while the best-performing model achieves a question-level accuracy of 0.90, its infographic-level accuracy drops to just 0.49, and data-related tasks such as Data Completeness score as low as 0.21. This highlights a significant gap between surface-level visual appeal and factual or structural correctness in AI-generated infographics.
A team of researchers has released IGenBench, a benchmark designed to systematically assess the reliability of text-to-infographic generation by current AI models. The benchmark comprises 600 test cases spanning 30 infographic types and uses an automated evaluation framework that breaks reliability verification into atomic yes/no questions organized under a taxonomy of 10 question types. Multimodal large language models (MLLMs) are employed to answer these questions, producing both question-level accuracy (Q-ACC) and infographic-level accuracy (I-ACC) scores. Evaluating 10 state-of-the-art text-to-image models, the study identifies a three-tier performance hierarchy: the top model reaches a Q-ACC of 0.90 but an I-ACC of only 0.49, meaning fewer than half of its generated infographics are fully correct end-to-end. Data-related dimensions, particularly Data Completeness (scoring 0.21), emerge as universal bottlenecks across all models. The findings suggest that current models can produce visually plausible infographics that nonetheless contain subtle but consequential errors in data encoding or textual content. The benchmark and associated resources have been publicly released to support future research.
What different sources said
- arXiv cs.LGCenter
IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.