mlsanityData to 7 Oct 2026

Cross-lingual Prompting: Improving Zero-shot Chain-of-Thought Reasoning across Languages

arXiv 2310.14799 ↗First posted 23 Oct 2023cs.CL cs.AIcited by 96

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

Abstract (arXiv)

Chain-of-thought (CoT) is capable of eliciting models to explicitly generate reasoning paths, thus promoting reasoning accuracy and attracting increasing attention. Specifically, zero-shot CoT achieves remarkable improvements in a wide range of reasoning tasks by simply instructing the LLM with the prompt "Let's think step by step!". Despite the success of zero-shot CoT, the existing zero-shot prompting techniques remain limited to a single language, making it challenging to generalize to other languages and hindering global development. In this work, we introduce cross-lingual prompting (CLP), aiming to improve zero-shot CoT reasoning across languages. Specifically, CLP consists of two main components: (1) cross-lingual alignment prompting and (2) task-specific solver prompting. The cross-lingual alignment prompting is responsible for aligning representations across different languages, whereas the task-specific solver prompting is used to generate the final chain of thoughts and results for the reasoning task. In addition, we further introduce cross-lingual self-consistent prompting (CLSP) to ensemble different reasoning paths across languages. Our experimental evaluations on several benchmarks demonstrate that CLP and CLSP significantly outperform the existing prompting methods and achieve state-of-the-art performance. We hope this work will inspire further breakthroughs in cross-lingual CoT.

Key facts. Cited by 96 papers in the map (data through 7 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 34 of its 45 references that are in the map. First posted on arXiv 23 Oct 2023.

Builds on

34 of 45 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022Large Language Models are Zero-Shot Reasoners24 May
  2. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Models21 May
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar

Other references · 31

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  7. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  8. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,219
  9. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,057
  10. 2018XNLI: Evaluating Cross-lingual Sentence Representationscited by 913
  11. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
  12. 2022Language Models are Multilingual Chain-of-Thought Reasonerscited by 518
19 more
  1. 2023Is ChatGPT a General-Purpose Natural Language Processing Task Solver?cited by 486
  2. 2023How Good Are GPT Models at Machine Translation? A Comprehensive Evaluationcited by 344
  3. 2020XCOPA: A Multilingual Dataset for Causal Commonsense Reasoningcited by 330
  4. 2023MEGA: Multilingual Evaluation of Generative AIcited by 291
  5. 2021Few-shot Learning with Multilingual Language Modelscited by 278
  6. 2019PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identificationcited by 262
  7. 2022ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoningcited by 175
  8. 2023Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Promptingcited by 163
  9. 2021Language Models are Few-shot Multilingual Learnerscited by 92
  10. 2022Language Contamination Helps Explain the Cross-lingual Capabilities of English Pretrained Modelscited by 90
  11. 2020CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLPcited by 79
  12. 2023Multilingual LLMs are Better Cross-lingual In-context Learners with Alignmentcited by 71
  13. 2021CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language Pairscited by 39
  14. 2022The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challengescited by 35
  15. 2023A Preliminary Evaluation of ChatGPT for Zero-shot Dialogue Understandingcited by 31
  16. 2022A Balanced Data Approach for Evaluating Cross-Lingual Transfer: Mapping the Linguistic Blood Bankcited by 29
  17. 2022GreenPLM: Cross-Lingual Transfer of Monolingual Pre-Trained Language Models at Almost No Costcited by 24
  18. 2022ALERT: Adapting Language Models to Reasoning Taskscited by 17
  19. 2023Towards Unifying Multi-Lingual and Cross-Lingual Summarizationcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 36; 2025: 45; 2026: 13.

96 papers.

Sort:

By area:

  1. 2024M3CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thoughtcited by 120
  2. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  3. 2024Large Language Models Meet NLP: A Surveycited by 102
  4. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agentscited by 72
  5. 2024MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimizationcited by 68
  6. 2024Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thoughtcited by 56
  7. 2024Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontierscited by 49
  8. 2024xCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoningcited by 46
  9. 2025Crosslingual Reasoning through Test-Time Scalingcited by 46
  10. 2024Question Translation Training for Better Multilingual Reasoningcited by 41
  11. 2024Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languagescited by 38
  12. 2024Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languagescited by 36
38 more
  1. 2025Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thoughtcited by 34
  2. 2024Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language Modelscited by 31
  3. 2024What Factors Affect Multi-Modal In-Context Learning? An In-Depth Explorationcited by 31
  4. 2024Language Imbalance Driven Rewarding for Multilingual Self-improvingcited by 27
  5. 2024Converging to a Lingua Franca: Evolution of Linguistic Regions and Semantics Alignment in Multilingual Large Language Modelscited by 22
  6. 2024Fine-tuning Large Language Models with Sequential Instructionscited by 20
  7. 2024Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Modelscited by 20
  8. 2025Language-Specific Latent Process Hinders Cross-Lingual Performancecited by 20
  9. 2025The Emergence of Abstract Thought in Large Language Models Beyond Any Languagecited by 20
  10. 2025MPO: Multilingual Safety Alignment via Reward Gap Optimizationcited by 18
  11. 2024PKRD-CoT: A Unified Chain-of-thought Prompting for Multi-Modal Large Language Models in Autonomous Drivingcited by 17
  12. 2025QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Languagecited by 16
  13. 2024CMMaTH: A Chinese Multi-modal Math Skill Evaluation Benchmark for Foundation Modelscited by 15
  14. 2024What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practicescited by 14
  15. 2024Better to Ask in English: Evaluation of Large Language Models on English, Low-resource and Cross-Lingual Settingscited by 14
  16. 2025AdaMCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Multilingual Chain-of-Thoughtcited by 14
  17. 2024Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learnerscited by 11
  18. 2025Enhancing Non-English Capabilities of English-Centric Large Language Models through Deep Supervision Fine-Tuningcited by 11
  19. 2025Improving Multilingual Language Models by Aligning Representations through Steeringcited by 11
  20. 2025Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?cited by 11
  21. 2024Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Informationcited by 10
  22. 2025X-WebAgentBench: A Multilingual Interactive Web Benchmark for Evaluating Global Agentic Systemcited by 10
  23. 20241+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators?cited by 9
  24. 2024GlobeSumm: A Challenging Benchmark Towards Unifying Multi-lingual, Cross-lingual and Multi-document News Summarizationcited by 9
  25. 2023Empowering Multi-step Reasoning across Languages via Tree-of-Thoughtscited by 8
  26. 2024Revealing the Parallel Multilingual Learning within Large Language Modelscited by 8
  27. 2024CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggerscited by 8
  28. 2025Just Go Parallel: Improving the Multilingual Capabilities of Large Language Modelscited by 8
  29. 2026Understanding Multilingualism in Mixture-of-Experts LLMs: Routing Mechanism, Expert Specialization, and Layerwise Steeringcited by 8
  30. 2024The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insightscited by 7
  31. 2025CCHall: A Novel Benchmark for Joint Cross-Lingual and Cross-Modal Hallucinations Detection in Large Language Modelscited by 7
  32. 2025Mimicking or Reasoning: Rethinking Multi-Modal In-Context Learning in Vision-Language Modelscited by 7
  33. 2024Do Large Language Models Speak All Languages Equally? A Comparative Study in Low-Resource Settingscited by 6
  34. 2024Prompting with Phonemes: Enhancing LLMs' Multilinguality for Non-Latin Script Languagescited by 6
  35. 2025Towards Better Understanding of Program-of-Thought Reasoning in Cross-Lingual and Multilingual Environmentscited by 6
  36. 2025What Makes a Good Natural Language Prompt?cited by 6
  37. 2025Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Studycited by 6
  38. 2025A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languagescited by 6

50 most cited of 96 All 96 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
  2. 2024Break the Chain: Large Language Models Can be Shortcut Reasoners
  3. 2024Zero-Shot Chain-of-Thought Reasoning Guided by Evolutionary Algorithms in Large Language Models
  4. 2024Instance-adaptive Zero-shot Chain-of-Thought Prompting
  5. 2024Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patterns
  6. 2026Diverge to Induce Prompting: Multi-Rationale Induction for Zero-Shot Reasoning
  7. 2022Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango
  8. 2024AutoCAP: Towards Automatic Cross-lingual Alignment Planning for Zero-shot Chain-of-Thought