Multilingual Conceptual Coverage in Text-to-Image Models

TL;DR

This paper introduces CoCo-CroLa, a benchmarking technique to evaluate how well text-to-image models provide consistent and equitable image generation across multiple languages, focusing on tangible nouns.

Contribution

The paper presents a novel method for assessing multilingual parity in text-to-image models, enabling evaluation of conceptual coverage across languages without prior assumptions.

Findings

CoCo-CroLa effectively benchmarks multilinguality in T2I models.

The technique reveals model-specific weaknesses and biases.

It serves as a good proxy for generalization in multilingual settings.

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.