AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Language Drift in Multilingual Retrieval-Augmented Generation: Characterization and Decoding-Time Mitigation

Bo Li, Zhenghua Xu, Rui Xie

AAAI 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation · 10 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
add Soft Constrained Decoding (boost target tokens, penalize distractor tokens)LLaMA3-8B-Instruct · HotpotQA (ZH target, EN context)language consistency: 68.4% -> 90.6%Improved
add SCDLLaMA3-8B-Instruct · HotpotQA (ZH target, EN context)ROUGE: 0.182 -> 0.306Improved
add SCDLLaMA3-8B-Instruct · MuSiQue (ZH target, EN context)language consistency: 63.9% -> 91.8%Improved
add SCD instead of translating outputs back after generation (ablation)LLaMA3-8B-Instruct · HotpotQA (ZH target, EN context)ROUGE: 0.263 -> 0.306Improved
use soft penalty (SCD) instead of hard vocabulary restriction (ablation)LLaMA3-8B-Instruct · HotpotQA (ZH target, EN context)ROUGE: 0.155 -> 0.306Improved
hard vocabulary restriction instead of prompted instruction (ablation)LLaMA3-8B-Instruct · HotpotQA (AR/RU targets)ROUGE: 0.294 -> 0.295 (AR); 0.333 -> 0.343 (RU)No clear effect
hard vocabulary restriction instead of prompted instruction (ablation)LLaMA3-8B-Instruct · HotpotQA (ZH target, EN context)ROUGE: 0.182 -> 0.155Hurt
switch retrieved context from ZH to EN (cross-lingual interference)LLaMA3-8B-Instruct with ICL · HotpotQA (ZH target)language consistency: 92.0% -> 68.4%Hurt
add in-context exemplarsLLaMA3-8B-Instruct · HotpotQA (RU target)ROUGE and language consistency: ROUGE 0.193 -> 0.373; LC 0.991 -> 0.895Mixed
translate drifted outputs back to the target language before scoringLLaMA3-8B-Instruct · HotpotQA (ZH target, EN context)ROUGE: 0.182 -> 0.263Improved

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