Localization Boosting for Growth Markets: Mitigating Cross-Locale Behavioral Bias in Learning-to-Rank
For platforms expanding internationally, this addresses the cross-locale exposure bias that suppresses local content discoverability in growth markets.
Adobe Express's LTR models over-serve US templates in non-US locales due to training on click data. A multi-objective framework with VLM relevance and locale-aware boosting improves relevance and restores local content visibility across five locales.
Adobe Express is expanding internationally, but the US has a disproportionately large content supply and interaction volume. Learning-to-rank (LTR) models trained primarily on behavioral feedback inherit this imbalance: templates popular in US are over-served in non-US locales. This cross-locale exposure bias suppresses local content discoverability and degrades ranking quality in growth locales. We show that click-only training suppresses semantically informative localization features. Adding vision-language model (VLM) graded relevance labels as auxiliary supervision alongside clicks improves semantic alignment but does not preserve local content visibility. We propose a multi-objective framework combining behavioral supervision, VLM-derived relevance signals, and locale-aware boosting. Across five locales, the resulting model improves relevance while restoring stable localization, demonstrating the importance of disentangling exposure from semantic supervision.