No One Fits All: From Fixed Prompting to Learned Routing in Multilingual LLMs
Translation-based prompting is widely used in multilingual LLMs, yet its effectiveness varies across languages and tasks. We evaluate prompting strategies across ten languages of different resource levels and four benchmarks. Our analysis shows that no single strategy is universally optimal. Translation strongly benefits low-resource languages even when translation quality is imperfect, high-resource languages gain little, and prompt-based self-routing underperforms explicit translation. Motivated by these findings, we formulate prompting strategy selection as a learned decision problem and introduce lightweight classifiers that predict whether native or translation-based prompting is optimal for each instance. The classifiers achieve statistically significant improvements over fixed strategies across four benchmarks and generalize to unseen task formats not observed during training. Further analysis reveals that language resource level, rather than translation quality alone, determines when translation is beneficial.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Multilingual Prompting for Improving LLM Generation Diversity
Large Language Models (LLMs) are known to lack cultural representation and overall diversity in their generations, from expressing opinions to answering factual questions. To mitigate this problem, we propose multilingua…
DiversityHallucinationMRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition
Multilingual text recognition (MLTR) systems typically focus on a fixed set of languages, which makes it difficult to handle newly added languages or adapt to ever-changing data distribution. In this paper, we propose th…
Continual LearningIncremental LearningOptical Character Recognition (OCR)Scene Text RecognitionSimpCue: Cue-Based Prompting for Multilingual Text Simplification
Text simplification aims to make complex texts easier to understand while preserving their original meaning. Recent large language models can perform simplification through prompting, but it remains unclear whether addin…
Text SimplificationFixing MoE Over-Fitting on Low-Resource Languages in Multilingual Machine Translation
Sparsely gated Mixture of Experts (MoE) models have been shown to be a compute-efficient method to scale model capacity for multilingual machine translation. However, for low-resource tasks, MoE models severely over-fit.…
Machine TranslationMixture-of-ExpertsTranslationRe-examining Routing Networks for Multi-task Learning
We re-examine Routing Networks, an approach to multi-task learning that uses reinforcement learning to decide parameter sharing with the goal of maximizing knowledge transfer between related tasks while avoiding task int…
Multi-Task Learningreinforcement-learningReinforcement Learning (RL)Transfer Learning