# How and Where to Translate? The Impact of Translation Strategies in Cross-lingual LLM Prompting

arXiv: https://arxiv.org/abs/2507.22923 · HTML: https://mlsanity.com/paper/2507.22923/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 32 references that are in the map.
- First posted on arXiv 21 Jul 2025.

## Builds on (most cited first, 14 of 14)

- [Language Models are Multilingual Chain-of-Thought Reasoners](https://mlsanity.com/paper/2210.03057/) (2022)
- [MEGA: Multilingual Evaluation of Generative AI](https://mlsanity.com/paper/2303.12528/) (2023)
- [ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning](https://mlsanity.com/paper/2304.05613/) (2023)
- [LLaMA Beyond English: An Empirical Study on Language Capability Transfer](https://mlsanity.com/paper/2401.01055/) (2024)
- [Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification](https://mlsanity.com/paper/2406.08660/) (2024)
- [LLMs Are Few-Shot In-Context Low-Resource Language Learners](https://mlsanity.com/paper/2403.16512/) (2024)
- [Lost in Translation: Large Language Models in Non-English Content Analysis](https://mlsanity.com/paper/2306.07377/) (2023)
- [CrisisSense-LLM: Instruction Fine-Tuned Large Language Model for Multi-label Social Media Text Classification in Disaster Informatics](https://mlsanity.com/paper/2406.15477/) (2024)
- [Intent Detection in the Age of LLMs](https://mlsanity.com/paper/2410.01627/) (2024)
- [Beyond English: The Impact of Prompt Translation Strategies across Languages and Tasks in Multilingual LLMs](https://mlsanity.com/paper/2502.09331/) (2025)
- [Translation Errors Significantly Impact Low-Resource Languages in Cross-Lingual Learning](https://mlsanity.com/paper/2402.02080/) (2024)
- [PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awareness](https://mlsanity.com/paper/2410.07035/) (2024)
- [REIC: RAG-Enhanced Intent Classification at Scale](https://mlsanity.com/paper/2506.00210/) (2025)
- [Multilingual Information Retrieval with a Monolingual Knowledge Base](https://mlsanity.com/paper/2506.02527/) (2025)

## Built on by (most cited first, 2 of 2)

- [RealityTest: How People Probe AI Identity and Whether Models Disclose It](https://mlsanity.com/paper/2606.00168/) (2026)
- [Translation Analytics for Freelancers II: Benchmarking Local LLMs for Confidential Translation Workflows](https://mlsanity.com/paper/2605.31452/) (2026)

## Abstract (arXiv)

Despite advances in the multilingual capabilities of Large Language Models (LLMs), their performance varies substantially across different languages and tasks. 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, resulting in retrieved information from the KB being in a different language than the rest of the context. In such scenarios, two common practices are pre-translation to create a mono-lingual prompt and cross-lingual prompting for direct inference. However, the impact of these choices remains unclear. In this paper, we systematically evaluate the impact of different prompt translation strategies for classification tasks with RAG-enhanced LLMs in multilingual systems. Experimental results show that an optimized prompting strategy can significantly improve knowledge sharing across languages, therefore improve the performance on the downstream classification task. The findings advocate for a broader utilization of multilingual resource sharing and cross-lingual prompt optimization for non-English languages, especially the low-resource ones.