Hybrid Batch Training Ratios and Zero-Shot Retrieval Accuracy on XTREME-R
Abstract
Description
<p>Information retrieval across different languages is an increasingly important challenge in natural language processing. Recent approaches based on multilingual pre-trained language models have achieved remarkable success, yet they often optimize for either monolingual, cross-lingual, or multilingual retrieval performance at the expense of others. This paper proposes a novel hybrid batch training strategy to simultaneously improve zero-shot retrieval performance across monolingual, cross-lingual, and multilingual settings while mitigating language bias. The approach fine-tunes multilingual lang</p><p><strong>Research goal:</strong> How does varying the ratio of monolingual to cross-lingual samples in hybrid batch training affect zero-shot retrieval accuracy on the XTREME-R benchmark compared to uniform sampling strategies?</p><p><em>Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.0/10.</em></p>
This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.0/10.
This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.0/10.
Keywords
Citation
Collections
Endorsement
Review
Supplemented By
Referenced By
Rights and licensing
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode