Localization Boosting for Growth Markets: Mitigating Cross-Locale Behavioral Bias in Learning-to-Rank
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909034240540672 |
|---|---|
| author | Seran, Suryaa Veerabathiran Kumar, Ashwin Naresh King, Tracy Holloway Zheng, Jing |
| author_facet | Seran, Suryaa Veerabathiran Kumar, Ashwin Naresh King, Tracy Holloway Zheng, Jing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_11272 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Localization Boosting for Growth Markets: Mitigating Cross-Locale Behavioral Bias in Learning-to-Rank Seran, Suryaa Veerabathiran Kumar, Ashwin Naresh King, Tracy Holloway Zheng, Jing Machine Learning Artificial Intelligence Information Retrieval 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. |
| title | Localization Boosting for Growth Markets: Mitigating Cross-Locale Behavioral Bias in Learning-to-Rank |
| topic | Machine Learning Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2605.11272 |