Navigating Text-to-Image Generative Bias across Indic Languages
It addresses generative bias for over 1.4 billion speakers of Indic languages, but is incremental as it applies existing evaluation methods to new data.
This research tackles biases in text-to-image models for Indic languages by evaluating their performance and cultural relevance compared to English, using a new benchmark that assesses 30 languages and finds significant gaps needing improvement.
This research investigates biases in text-to-image (TTI) models for the Indic languages widely spoken across India. It evaluates and compares the generative performance and cultural relevance of leading TTI models in these languages against their performance in English. Using the proposed IndicTTI benchmark, we comprehensively assess the performance of 30 Indic languages with two open-source diffusion models and two commercial generation APIs. The primary objective of this benchmark is to evaluate the support for Indic languages in these models and identify areas needing improvement. Given the linguistic diversity of 30 languages spoken by over 1.4 billion people, this benchmark aims to provide a detailed and insightful analysis of TTI models' effectiveness within the Indic linguistic landscape. The data and code for the IndicTTI benchmark can be accessed at https://iab-rubric.org/resources/other-databases/indictti.