Localization Boosting for Growth Markets: Mitigating Cross-Locale Behavioral Bias in Learning-to-Rank

TL;DR

This paper presents a multi-objective learning framework that combines behavioral feedback, vision-language relevance, and locale-aware boosting to improve content ranking and localization in growth markets.

Contribution

It introduces a novel multi-objective approach that mitigates cross-locale bias and enhances local content discoverability in learning-to-rank models.

Findings

Improved relevance across five locales.

Restored localization stability.

Enhanced semantic alignment with VLM signals.

Abstract

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.