arXiv Computer Vision
Whose Values Are Generated? Measuring Visual Value Leakage in Multilingual Text-to-Image Generation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Sep 12
Prompt Revision as a Source of Cultural Bias in Text-to-Image Systems
The paper "Prompt Revision as a Source of Cultural Bias in Text-to-Image Systems" investigates how commercial text‑to‑image models silently modify user prompts before generating images, a step that is often hidden from users. Using the multilingual benchmark WORLDVIEW, the authors audit the revision layer in DALL‑E‑3, Imagen‑4, and GPT‑Image‑1.5, finding that non‑Western and non‑Anglophone contexts are disproportionately marked, reduced to narrow vocabularies, and stereotyped. The study demonstrates that the revision layer itself is a previously undocumented causal source of cultural stereotyping, underscoring the need to audit deployed systems rather than just the underlying models.
arXiv AI
Jul 3
Cross-Cultural Value Attribution in Large Vision-Language Models
arXiv:2604. 09945v2 Announce Type: replace-cross Abstract: The rapid adoption of large vision-language models (LVLMs) in recent years has been accompanied by growing fairness concerns due to their propensity to reinforce harmful societal stereotypes.
arXiv AI
Aug 12
On the Limitations of Cross-Lingual Consistency in Multilingual Text-to-image Generation
arXiv:2608. 11002v1 Announce Type: cross Abstract: Text-to-image (T2I) generation has achieved remarkable progress in recent years.
arXiv Computation and Language
Aug 28
CultureVidBench: Benchmarking Cultural Understanding in Text-to-Video Generation
CultureVidBench is a new benchmark that evaluates how well text‑to‑video generation models capture cultural details. It contains 1,000 prompts spanning 12 countries, 6 continents, 8 cultural regions, and 14 cultural aspects, grouped into material culture, social practice & performance, and ritual & ceremony. Human studies and automated assessments show that while current models perform well on semantic adherence and visual quality, they often miss fine‑grained cultural details, especially for underrepresented regions and multimodal cues.
arXiv AI
Jul 21
When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation
arXiv:2605. 16716v5 Announce Type: replace-cross Abstract: Text-to-video (T2V) generation has rapidly progressed in visual fidelity, yet its ability to faithfully represent multiple cultures within a single prompt remains underexplored.
arXiv Computer Vision
Oct 26
Playing Bias: Epistemic Games for Interpreting Text-to-Image Models
The paper "Playing Bias: Epistemic Games for Interpreting Text-to-Image Models" proposes a three-stage, humanities-informed framework—Interpret, Interrogate, and Expose—to make the cultural work of text-to-image (T2I) systems visible and debatable. These epistemic games, tested with undergraduate fine‑arts students, shift discussions from impressionistic reactions to concise, evidence‑based hypotheses, using lightweight classroom tools for reproducibility and structured collaboration. The authors argue that such game‑based approaches foster critical literacy, enabling learners to recognize, discuss, and contest how T2I models encode bias.