AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAG

Dayeon Ki, Marine Carpuat, Paul McNamee, Daniel Khashabi, Eugene Yang, Dawn Lawrie, Kevin Duh

ICML 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
translate the cited document from English to Swahili (ablation)six open-weight LLMs · ELI5 citation predictioncitation accuracy (%): AYA23 8B: 60.0 -> 22.4; Qwen3 8B: 62.6 -> 30.4Hurt
translate the cited document from English to Bengali (ablation)six open-weight LLMs · ELI5 citation predictioncitation accuracy (%): AYA23 8B: 60.0 -> 27.2Hurt
translate the cited document from English to French or Spanish (ablation)six open-weight LLMs · ELI5 citation predictioncitation accuracy (%): average -8.82% (French), -8.08% (Spanish)Hurt
place the cited document in the middle of the context (ablation)six open-weight LLMs · ELI5 citation predictionEnglish preference gap: largest accuracy gap vs English in the middle positionHurt
increase model size (ablation)Llama/Qwen3/Gemma-3 models · ELI5 English citation accuracycitation accuracy (%): Qwen3 8B 62.6 -> Qwen3 14B 83.0Improved
use a multilingual-trained model (Aya23 8B) (ablation)Aya23 8B · ELI5 citation predictionEnglish preferenceNo clear effect
query in target language, cited document in query language and other documents in English (ablation)six open-weight LLMs · ELI5, translated queriescitation accuracy: highest accuracy in 28 of 48 model-language pairsImproved
make all documents match the query language instead of only the cited one (ablation)six open-weight LLMs · ELI5, translated queriescitation accuracy: language contrast variant generally beats all-query-language variantNo clear effect
put relevant document in target language with irrelevant English distractor (ablation)six open-weight LLMs · MIRACL English dev (231 queries)citation accuracyHurt
put irrelevant distractor in target language, relevant document in English (ablation)six open-weight LLMs · MIRACL English dev (231 queries)citation accuracyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy