Research
No One Fits All: From Fixed Prompting to Learned Routing in Multilingual LLMs
arXiv:2604.16937v1 Announce Type: new Abstract: Translation-based prompting is widely used in multilingual LLMs, yet its effectiveness varies across languages and tasks. We evaluate prompting strategi
arXiv:2604.16937v1 Announce Type: new Abstract: 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.
Related
- Adaptive Multi-Expert Reasoning via Difficulty-Aware Routing and Uncertainty-Guided Aggregation
- Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios
- x1: Learning to Think Adaptively Across Languages and Cultures
- Think Multilingual, Not Harder: A Data-Efficient Framework for Teaching Reasoning Models to Code-Switch
- Cosine-Similarity Routing with Semantic Anchors for Interpretable Mixture-of-Experts Language Models
Source: arXiv cs.CL | 2026-04-21