What Drives Cross-lingual Ranking? Retrieval Approaches With Multilingual Language Models

Abstract

Cross-lingual information retrieval (CLIR) enables access to multilingual knowledge but remains challenging due to disparities in resources, scripts, and weak cross-lingual semantic alignment in embedding models. Existing pipelines often rely on translation and monolingual retrieval heuristics, which add computational overhead and noise, degrading performance. This work systematically evaluates four intervention types, namely document translation, multilingual dense retrieval with pretrained encoders, contrastive learning at word, phrase, and query-document levels, and cross-encoder re-ranking, across three benchmark datasets. We find that dense retrieval models trained specifically for CLIR consistently outperform lexical matching methods and derive little benefit from document translation. Contrastive learning mitigates language biases and yields substantial improvements for encoders with weak initial alignment, and re-ranking can be effective, but depends on the quality of the cross

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygoworek2025what

Related papers

• Bridging Language Gaps: Advances In Cross-lingual Information Retrieval With Multilingual Llms (2025)0.00
• On Cross-lingual Retrieval With Multilingual Text Encoders (2021)10.35
• Boosting Zero-shot Cross-lingual Retrieval By Training On Artificially Code-switched Data (2023)4.52
• Evaluating Multilingual Text Encoders For Unsupervised Cross-lingual Retrieval (2021)7.50
• Improving Cross-lingual Information Retrieval On Low-resource Languages Via Optimal Transport Distillation (2023)10.07
• Translate-distill: Learning Cross-language Dense Retrieval By Translation And Distillation (2024)8.60
• Transfer Learning Approaches For Building Cross-language Dense Retrieval Models (2022)10.97
• Clirudit: Cross-lingual Information Retrieval Of Scientific Documents (2025)0.00