mlsanityData to 7 Oct 2026

When Language Shapes Thought: Cross-Lingual Transfer of Factual Knowledge in Question Answering

arXiv 2505.24409 ↗First posted 30 May 2025cs.CL cs.AIcited by 2

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Multilingual large language models (LLMs) offer promising opportunities for cross-lingual information access, yet their use of factual knowledge remains highly sensitive to the input language. Prior work has addressed this through English prompting and evaluation, assuming that English-based reasoning is universally beneficial. In this work, we challenge that assumption by exploring factual knowledge transfer from non-English to English through the lens of Language and Thought Theory. We introduce Language-to-Thought (L2T) prompting, which aligns the model's internal ''thinking'' language with the source of knowledge. Across three languages and four models, L2T consistently outperforms English-based reasoning, reversing the expected advantage of English prompts. Our code is available at https://github.com/GeomeunByeol/Language2Thought.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 31 of its 38 references that are in the map. First posted on arXiv 30 May 2025.

Builds on

31 of 38 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers7 Apr
  2. 2024ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic20 Feb
  3. 2024xCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning13 Jan
  4. 2023Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs8 Nov
  5. 2023Do Multilingual Language Models Think Better in English?2 Aug
  6. 2023Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting11 May

Other references · 25

  1. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  2. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  4. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  5. 2019Language Models as Knowledge Bases?cited by 1,922
  6. 2022Language Models are Multilingual Chain-of-Thought Reasonerscited by 518
  7. 2023CMMLU: Measuring massive multitask language understanding in Chinesecited by 436
  8. 2022Reasoning with Language Model Prompting: A Surveycited by 251
  9. 2022Demystifying Prompts in Language Models via Perplexity Estimationcited by 215
  10. 2023InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviewscited by 177
  11. 2023Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMscited by 175
  12. 2024How do Large Language Models Handle Multilingualism?cited by 148
13 more
  1. 2023Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Modelscited by 117
  2. 2023Don't Trust ChatGPT when Your Question is not in English: A Study of Multilingual Abilities and Types of LLMscited by 103
  3. 2023Cross-lingual Prompting: Improving Zero-shot Chain-of-Thought Reasoning across Languagescited by 96
  4. 2023SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoningcited by 94
  5. 2024How Do Large Language Models Acquire Factual Knowledge During Pretraining?cited by 86
  6. 2024CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Koreancited by 65
  7. 2020EXAMS: A Multi-Subject High School Examinations Dataset for Cross-Lingual and Multilingual Question Answeringcited by 60
  8. 2023Revisiting Machine Translation for Cross-lingual Classificationcited by 40
  9. 2024Probing the Emergence of Cross-lingual Alignment during LLM Trainingcited by 38
  10. 2024Understanding Cross-Lingual Alignment -- A Surveycited by 34
  11. 2023Improving In-context Learning of Multilingual Generative Language Models with Cross-lingual Alignmentcited by 33
  12. 2022Match the Script, Adapt if Multilingual: Analyzing the Effect of Multilingual Pretraining on Cross-lingual Transferabilitycited by 26
  13. 2024Multilingual Brain Surgeon: Large Language Models Can be Compressed Leaving No Language Behindcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Multilingual Unlearning in LLMs: Transfer, Dynamics, and Reversibilitycited by 2
  2. 2026Mind the Gap: Pitfalls of LLM Alignment with Asian Public Opinioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Rethinking the Multilingual Reasoning Gap with Layer Swap
  2. 2025The Reasoning Lingua Franca: A Double-Edged Sword for Multilingual AI
  3. 2025A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages
  4. 2026Large Reasoning Models Struggle to Transfer Parametric Knowledge Across Scripts
  5. 2025AdaMCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Multilingual Chain-of-Thought
  6. 2025Language-Specific Latent Process Hinders Cross-Lingual Performance
  7. 2024The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights
  8. 2026Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning