Keywords: generative model, text-to-image, diffusion, dalle, stable diffusion, multilingual, model analysis, benchmark, concepts
TL;DR: We introduce an automated evaluation of the the multilingual `conceptual coverage' of generative text-to-image models using an aligned list of nouns across 7 languages, and novel correctness, consistency, and distinctiveness image population metrics.
Abstract: We propose "Conceptual Coverage Across Languages" (CoCo-CroLa), a technique for benchmarking the degree to which any generative text-to-image system provides multilingual parity to its training language in terms of tangible nouns. For each model we can assess "conceptual coverage" of a given target language relative to a source language by comparing the population of images generated for a series of tangible nouns in the source language to the population of images generated for each noun under translation in the target language. This technique allows us to estimate how well-suited a model is to a target language as well as identify model-specific weaknesses, spurious correlations, and biases without a-priori assumptions. We demonstrate how it can be used to benchmark T2I models in terms of multilinguality, and how despite its simplicity it is a good proxy for impressive generalization.