Year: 2026
Type: conference-paper
Abstract: Multilingual retrieval increasingly underpins cross-lingual question answering and retrievalaugmented generation.Strong zero-shot scores on multilingual benchmarks are often taken as evidence that current encoders transfer reliably across many languages.We argue that this assumption breaks down for underrepresented, morphologically rich languages, and use Amharic as a diagnostic case.Under a shared passage retrieval protocol covering dense, late-interaction, learned sparse, and cross-encoder paradigms, we compare zero-shot multilingual retrievers, Amharic-finetuned multilingual retrievers, and monolingual Amharic retrievers.The strongest zeroshot multilingual retriever underperforms the strongest monolingual Amharic first-stage retriever by 23% relative [email protected] two recent multilingual embedding models on the same Amharic supervision yields 32-60% relative MRR@10 gains over zero-shot, but the best Amharic-fine-tuned multilingual model remains below the strongest monolingual Amharic retriever.These findings indicate that zero-shot multilingual retrieval is not a sufficient proxy for equitable information access in the LLM era: for underrepresented languages, retrieval must be evaluated and adapted in-language rather than inferred from aggregate multilingual benchmarks.To foster future research, we publicly release the dataset, codebase, and trained models. 1
Institution: University of Amsterdam
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166799098