Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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

About

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.

Suryaa Veerabathiran Seran, Ashwin Naresh Kumar, Tracy Holloway King, Jing Zheng• 2026

Related benchmarks

TaskDatasetResultRank
Learning to RankDE (Germany) region query set (test)
Precision@2081
2
Learning to RankGB (Great Britain) region query set (test)
Precision@2088
2
Learning to RankJP (Japan) region query set (test)
Precision@2084
2
Learning to RankFR (France) region query set (test)
Precision@2082
2
RankingAdobe Express template interaction logs (US)
Ranking Quality0.68
2
RankingAdobe Express template interaction logs (DE)
Ranking Quality67.3
2
RankingAdobe Express template interaction logs FR
Ranking Quality66.4
2
RankingAdobe Express template interaction logs (GB)
Ranking Quality0.682
2
RankingAdobe Express template interaction logs (JP)
Ranking Quality0.714
2
Learning to RankUS (United States) region query set (test)
Prec@2067
2
Showing 10 of 10 rows

Other info

Follow for update