Pick the right embedding model for cross-lingual retrieval over 30 languages

MCQ·Medium·4.0 · 0·~1 min

Attempt it

For retrieval across many languages, the right answer is to pick an embedder that was explicitly trained on multilingual data. BGE-M3 from BAAI and multilingual-e5-large from Microsoft are the standard open-weights choices. Cohere embed-multilingual-v3 is the standard hosted choice. These models are trained with a shared embedding space across languages. A query in Spanish and a document in Japanese can land near each other in vector space if they are semantically related. That is the property you need for cross-lingual retrieval. The other options in the question all fail. Picking text-embedding-3-large because of MTEB rank ignores that MTEB is English-dominant; the leaderboard score does not predict multilingual quality. Assuming multilingual capability 'comes for free' from any modern transformer is wrong and shows up immediately in benchmarks. Pre-translating all documents to English adds a translation step in the critical path, which means latency, cost, and a new failure mode (bad translations producing bad retrieval). For a workload across 30 languages including non-Latin scripts, BGE-M3 is the canonical pick.

**The answer is BGE-M3 (or multilingual-e5-large, or Cohere embed-multilingual-v3).** These models are explicitly trained on multilingual data with a shared embedding space across languages. Which is exactly what cross-lingual retrieval requires. The other options in the question each fail a specific way. - **text-embedding-3-large** is English-dominant. Its MTEB score is computed primarily on English tasks. Throw non-Latin script at it and you get vectors clustered in a poorly-trained region of space: high mean cosine to each other, low correlation with actual semantic content, silent recall collapse on non-English queries. - **'Any English model works'** is the most expensive belief in multilingual RAG. Empirically, English-only models score in the 30s on MIRACL (the multilingual retrieval benchmark) while explicitly-multilingual models score in the 60s. - Pre-translate everything to English adds a translation-quality failure mode to the critical path. Translation errors compound with embedding errors. Latency and cost increase. The pattern is rarely worth it when an actually-multilingual embedder exists. **Why BGE-M3 specifically.** Beyond the shared multilingual space, it produces three output types from one forward pass: dense, sparse (learned BM25-style), and multi-vector (ColBERT-style). This makes hybrid retrieval cheap and natural.

Quick reference

TL;DR

Use an explicitly multilingual embedder (BGE-M3 or Cohere embed-multilingual-v3) for cross-lingual retrieval; English-only models silently degrade and pre-translation introduces a new failure mode on the critical path.

Memory aid

Easy to grasp

Imagine asking a librarian to organize a library so readers in five different languages can all find their books. A librarian fluent in all five languages will file each book where every reader can find it, regardless of the language. A librarian fluent only in English will file the English books beautifully and dump the rest into one 'foreign' pile where no reader can find anything specific. Search tools follow the same rule. Pick one trained on many languages and every reader gets a useful shelf. Pick one trained only on English and the non-English books end up in a useless corner.

Key concepts

Embeddings RAG Vector databases

Detailed answer & concept explanation

~7 min read

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example.

Quick scan · 2–4 min

Everything important, quickly.

6 minutes: shared multilingual space, BGE-M3 three outputs, why English-only fails on non-Latin scripts, pre-translation as anti-pattern.

Real-world examples

Real products, models, and research that use this idea.

Many global customer-support RAG deployments default to BGE-M3 or Cohere multilingual to avoid per-language pipelines.
Major search products serving non-English markets (Yandex, Naver, Baidu) rely on multilingual or language-specific embedders, not English-only ones.
Pinecone and Weaviate documentation explicitly recommend multilingual embedders for cross-lingual workloads rather than translation pipelines.
The MIRACL benchmark from Hugging Face measures cross-lingual retrieval and shows the gap between English-only and explicitly-multilingual models.

Interviewer follow-ups

What an interviewer would ask next. Try answering before peeking at the approach.

QHow would you validate BGE-M3 versus Cohere embed-multilingual-v3 on your specific language mix?

QWhen does pre-translation make sense as part of a multilingual pipeline?

QHow do you handle a mixed-script document that contains both English and Chinese in the same text block?

Don't say this

Red flags and common mistakes that signal junior thinking. Click to expand.

Most common mistake

Picking text-embedding-3-large for a multilingual workload because of its high MTEB score and shipping a system that silently fails on non-Latin scripts.

60-second cheat sheet

The night-before-the-interview bullets. Scan these on the way to the call.

References

Primary sources. Skim if you want the original framing.