Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Scaling Performance of Zero-Shot Cross-Lingual Retrieval Models with Model Size on Adversarial Benchmarks

Domain:

natural language processing

Record type:

paper
Creator:
Ass
Publisher:
Zenodo
Host:avatar
Transferring information retrieval (IR) models from a high-resource language (typically English) to other languages in a zero-shot fashion has become a widely adopted approach. In this work, we show that the effectiveness of zero-shot rankers diminishes when queries and documents are present in different languages. Motivated by this, we propose to train ranking models on artificially code-switched data instead, which we generate by utilizing bilingual lexicons. To this end, we experiment with lexicons induced from (1) cross-lingual word embeddings and (2) parallel Wikipedia page titles. We use Research goal: How does the performance of zero-shot cross-lingual retrieval models trained on code-switched data scale with increasing model size, as measured by accuracy degradation on adversarial or low-resource language benchmarks like XNLI? Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.5/10.

Visit

doi.orgzenodo.org

Tasks

information retrieval

Tags

performancezero-shotcross-lingualretrievalmodelstrainedcode-switcheddata

Licenses

Creative Commons Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/legalcode

Similar

Performance of Zero-Shot Cross-Lingual Retrieval Models on Low-Resource Languages with Adversarial Code-Switched TrainingScaling Student Model Size and Optimal Transport Distillation Performance in Cross-Lingual Zero-Shot Retrieval for Low-ResourceScaling Model Size for Zero-Shot Cross-Lingual Retrieval on Code-Switched Data in Low-Resource LanguagesImpact of XLM-R Model Scaling with Adversarial Pre-training on Zero-shot Cross-lingual Performance in XTREME-RScaling Model Size and Zero-Shot Cross-Lingual Transfer Performance in Low-Resource LanguagesScaling Model Size Effects on Zero-Shot Cross-Lingual Transfer in XTREME Benchmark

Performance of Zero-Shot Cross-Lingual Retrieval Models on Low-Resource Languages with Adversarial Code-Switched Training

Transferring information retrieval (IR) models from a high-resource language (typically English) to

Scaling Student Model Size and Optimal Transport Distillation Performance in Cross-Lingual Zero-Shot Retrieval for Low-Resource

Benefiting from transformer-based pre-trained language models, neural ranking models have made signi

Scaling Model Size for Zero-Shot Cross-Lingual Retrieval on Code-Switched Data in Low-Resource Languages

Benefiting from transformer-based pre-trained language models, neural ranking models have made signi

Impact of XLM-R Model Scaling with Adversarial Pre-training on Zero-shot Cross-lingual Performance in XTREME-R

Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potentia

Scaling Model Size and Zero-Shot Cross-Lingual Transfer Performance in Low-Resource Languages

Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potentia

Scaling Model Size Effects on Zero-Shot Cross-Lingual Transfer in XTREME Benchmark

Intermediate-task training---fine-tuning a pretrained model on an intermediate task before fine-tuni