Robustness of Zero-Shot Cross-Lingual Retrieval Models on Adversarial MIRACL Benchmark

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 robustness of zero-shot cross-lingual retrieval models trained on code-switched data degrade when evaluated on adversarial examples in the MIRACL benchmark, and how does this compare to models trained on monolingual data?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10.