No One Fits All: From Fixed Prompting to Learned Routing in Multilingual LLMs

• URL: http://arxiv.org/abs/2604.16937v2
• Date: Tue, 21 Apr 2026 03:26:34 GMT
• Title: No One Fits All: From Fixed Prompting to Learned Routing in Multilingual LLMs
• Abstract summary: We evaluate prompting strategies across ten languages of different resource levels and four benchmarks.<n>We introduce lightweight classifiers that predict whether native or translation-based prompting is optimal for each instance.
• Score: 22.409170147732464
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 papers

• Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs [51.56484100374058]
  Large Language Models (LLMs) demonstrate remarkable multilingual fluency, but their internal knowledge representations remain disproportionately biased toward high-resource languages.<n>We investigate whether these biases can be mitigated at inference time, forcing an English-prompted model to answer as if it were queried in target languages.<n>Experiments on Gemma 3 12B Instruct reveal persona prompting to be the strongest overall intervention, balancing efficacy, safety, and out-of-domain generalization.
  arXiv  Detail & Related papers  (2026-07-21T16:15:05Z)
• From Script to Semantics: Prompting Strategies for African NLI [1.0705399532413615]
  We present a systematic study of prompting strategies for Natural Language Inference (NLI) in Swahili, Yoruba, and Hausa.<n>We evaluate five prompting strategies Baseline (zero-shot), Script-Aware, Language Specific, Contrastive, and Native-Label Self-Translation (NL-STP)<n>We find a significant difference in performance of class wise across strategies with highly neutral class collapse and high prediction skew in some configurations.
  arXiv  Detail & Related papers  (2026-06-02T08:20:10Z)
• Learning to Route Languages for Multilingual Policy Optimization [50.044784120224335]
  Large language models are trained on heterogeneous multilingual corpora.<n>We propose language-routed policy optimization (LRPO), an online policy optimization framework that treats language as a selectable variable.
  arXiv  Detail & Related papers  (2026-05-25T02:28:41Z)
• Investigating Language and Retrieval Bias in Multilingual Previously Fact-Checked Claim Detection [4.6738956348193]
  Large Language Models (LLMs) offer powerful capabilities for cross-lingual fact-checking.<n>LLMs often exhibit language bias, performing disproportionately better on high-resource languages such as English.<n>We present and inspect a novel concept - retrieval bias, when information retrieval systems tend to favor certain information over others.
  arXiv  Detail & Related papers  (2025-09-29T17:50:32Z)
• How and Where to Translate? The Impact of Translation Strategies in Cross-lingual LLM Prompting [15.388822834013599]
  In multilingual retrieval-augmented generation (RAG)-based systems, knowledge bases (KB) are often shared from high-resource languages (such as English) to low-resource ones.<n>Two common practices are pre-translation to create a mono-lingual prompt and cross-lingual prompting for direct inference.<n>We show that an optimized prompting strategy can significantly improve knowledge sharing across languages, therefore improve the performance on the downstream classification task.
  arXiv  Detail & Related papers  (2025-07-21T19:37:15Z)
• Beyond English: The Impact of Prompt Translation Strategies across Languages and Tasks in Multilingual LLMs [13.458891794688551]
  We evaluate pre-translation strategies across 35 languages covering both low and high-resource languages.<n>Our experiments show the impact of factors as similarity to English, translation quality and the size of pre-trained data, on the model performance with pre-translation.
  arXiv  Detail & Related papers  (2025-02-13T13:49:30Z)
• SMILE: Speech Meta In-Context Learning for Low-Resource Language Automatic Speech Recognition [55.2480439325792]
  Speech Meta In-Context LEarning (SMILE) is an innovative framework that combines meta-learning with speech in-context learning (SICL)<n>We show that SMILE consistently outperforms baseline methods in training-free few-shot multilingual ASR tasks.
  arXiv  Detail & Related papers  (2024-09-16T16:04:16Z)
• Chain-of-Translation Prompting (CoTR): A Novel Prompting Technique for Low Resource Languages [0.4499833362998489]
  Chain of Translation Prompting (CoTR) is a novel strategy designed to enhance the performance of language models in low-resource languages.<n>CoTR restructures prompts to first translate the input context from a low-resource language into a higher-resource language, such as English.<n>We demonstrate the effectiveness of this method through a case study on the low-resource Indic language Marathi.
  arXiv  Detail & Related papers  (2024-09-06T17:15:17Z)
• Analyzing and Adapting Large Language Models for Few-Shot Multilingual NLU: Are We There Yet? [82.02076369811402]
  Supervised fine-tuning (SFT), supervised instruction tuning (SIT) and in-context learning (ICL) are three alternative, de facto standard approaches to few-shot learning. We present an extensive and systematic comparison of the three approaches, testing them on 6 high- and low-resource languages, three different NLU tasks, and a myriad of language and domain setups. Our observations show that supervised instruction tuning has the best trade-off between performance and resource requirements.
  arXiv  Detail & Related papers  (2024-03-04T10:48:13Z)
• Investigating Multi-Pivot Ensembling with Massively Multilingual Machine Translation Models [47.91306228406407]
  We revisit ways of pivoting through multiple languages. We propose MaxEns, a novel combination strategy that makes the output biased towards the most confident predictions. On average, multi-pivot strategies still lag behind using English as a single pivot language.
  arXiv  Detail & Related papers  (2023-11-13T16:15:20Z)
• Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts [75.33019401706188]
  Large language models (LLMs) are known to effectively perform tasks by simply observing few exemplars. We propose to assemble synthetic exemplars from a diverse set of high-resource languages to prompt the LLMs to translate from any language into English. Our unsupervised prompting method performs on par with supervised few-shot learning in LLMs of different sizes for translations between English and 13 Indic and 21 African low-resource languages.
  arXiv  Detail & Related papers  (2023-06-20T08:27:47Z)
• Analyzing and Reducing the Performance Gap in Cross-Lingual Transfer with Fine-tuning Slow and Fast [50.19681990847589]
  Existing research has shown that a multilingual pre-trained language model fine-tuned with one (source) language also performs well on downstream tasks for non-source languages. This paper analyzes the fine-tuning process, discovers when the performance gap changes and identifies which network weights affect the overall performance most.
  arXiv  Detail & Related papers  (2023-05-19T06:04:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.