mlsanityData to 7 Oct 2026

Large Language Models are Good Multi-lingual Learners : When LLMs Meet Cross-lingual Prompts

arXiv 2409.11056 ↗First posted 17 Sep 2024cs.CLcited by 10

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

With the advent of Large Language Models (LLMs), generating rule-based data for real-world applications has become more accessible. Due to the inherent ambiguity of natural language and the complexity of rule sets, especially in long contexts, LLMs often struggle to follow all specified rules, frequently omitting at least one. To enhance the reasoning and understanding of LLMs on long and complex contexts, we propose a novel prompting strategy Multi-Lingual Prompt, namely MLPrompt, which automatically translates the error-prone rule that an LLM struggles to follow into another language, thus drawing greater attention to it. Experimental results on public datasets across various tasks have shown MLPrompt can outperform state-of-the-art prompting methods such as Chain of Thought, Tree of Thought, and Self-Consistency. Additionally, we introduce a framework integrating MLPrompt with an auto-checking mechanism for structured data generation, with a specific case study in text-to-MIP instances. Further, we extend the proposed framework for text-to-SQL to demonstrate its generation ability towards structured data synthesis.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 21 of its 61 references that are in the map. First posted on arXiv 17 Sep 2024.

Builds on

21 of 61 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Models6 Oct

Other references · 20

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  5. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  6. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,968
  7. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,928
  8. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  9. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
  10. 2024DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Modelcited by 1,093
  11. 2015Teaching Machines to Read and Comprehendcited by 1,039
  12. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,026
8 more
  1. 2017The NarrativeQA Reading Comprehension Challengecited by 590
  2. 2023The Falcon Series of Open Language Modelscited by 526
  3. 2023OpenChat: Advancing Open-source Language Models with Mixed-Quality Datacited by 250
  4. 2024Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?cited by 55
  5. 2024Synthesizing Text-to-SQL Data from Weak and Strong LLMscited by 53
  6. 2023Transferable Adversarial Attacks on Vision Transformers with Token Gradient Regularizationcited by 42
  7. 2023A Deep Instance Generative Framework for MILP Solvers Under Limited Data Availabilitycited by 21
  8. 2024Leveraging Large Language Models for Solving Rare MIP Challengescited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 7; 2026: 3.

10 papers.

  1. 2025The Emergence of Abstract Thought in Large Language Models Beyond Any Languagecited by 20
  2. 2025Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Modelscited by 18
  3. 2025Disentangling Language and Culture for Evaluating Multilingual Large Language Modelscited by 15
  4. 2025Synthetic Data Generation for Phrase Break Prediction with Large Language Modelcited by 2
  5. 2025XL-Suite: Cross-Lingual Synthetic Training and Evaluation Data for Open-Ended Generationcited by 1
  6. 2025SAGE: Strategy-Adaptive Generation Engine for Query Rewritingcited by 1
  7. 2026OSCAR: Optimization-Steered Agentic Planning for Composed Image Retrievalcited by 1
  8. 2025Improving Translation Quality by Selecting Better Data for LLM Fine-Tuning: A Comparative Analysiscited by 0
  9. 2026Benchmarking Concept-Spilling Across Languages in LLMscited by 0
  10. 2026Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Frameworkcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025EMCEE: Improving Multilingual Capability of LLMs via Bridging Knowledge and Reasoning with Extracted Synthetic Multilingual Context
  2. 2023Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting
  3. 2025Cross-Lingual Prompt Steerability: Towards Accurate and Robust LLM Behavior across Languages
  4. 2024Multilingual Large Language Models: A Systematic Survey
  5. 2025How and Where to Translate? The Impact of Translation Strategies in Cross-lingual LLM Prompting
  6. 2025Probing Large Language Models in Reasoning and Translating Complex Linguistic Puzzles
  7. 2023How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settings
  8. 2025Learned-Rule-Augmented Large Language Model Evaluators