mlsanityData to 14 Oct 2026

Could Thinking Multilingually Empower LLM Reasoning?

arXiv 2504.11833 ↗First posted 16 Apr 2025cs.CLcited by 16

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Previous work indicates that large language models exhibit a significant "English bias", i.e. they often perform better when tasks are presented in English. Interestingly, we have observed that using certain other languages in reasoning tasks can yield better performance than English. However, this phenomenon remains under-explored. In this paper, we explore the upper bound of harnessing multilingualism in reasoning tasks, suggesting that multilingual reasoning promises significantly (by nearly 10 Acc@k points) and robustly (tolerance for variations in translation quality and language choice) higher upper bounds than English-only reasoning. Besides analyzing the reason behind the upper bound and challenges in reaching it, we also find that common answer selection methods cannot achieve this upper bound, due to their limitations and biases. These insights could pave the way for future research aimed at fully harnessing the potential of multilingual reasoning in LLMs.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 19 of its 48 references that are in the map. First posted on arXiv 16 Apr 2025.

Builds on

19 of 48 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024xCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning13 Jan
  2. 2023LLaMA: Open and Efficient Foundation Language Models27 Feb

Other references · 17

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  6. 2024Qwen2.5 Technical Reportcited by 4,942
  7. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  8. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  9. 2025s1: Simple test-time scalingcited by 1,341
  10. 2022Galactica: A Large Language Model for Sciencecited by 744
  11. 2024From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipelinecited by 500
  12. 2023Structured Chain-of-Thought Prompting for Code Generationcited by 138
5 more
  1. 2023Self-planning Code Generation with Large Language Modelscited by 124
  2. 2025CodeI/O: Condensing Reasoning Patterns via Code Input-Output Predictioncited by 55
  3. 2024To Code, or Not To Code? Exploring Impact of Code in Pre-trainingcited by 47
  4. 2025BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Modelscited by 23
  5. 2023Exploring Equation as a Better Intermediate Meaning Representation for Numerical Reasoningcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 11.

16 papers.

Sort:

By area:

  1. 2025When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasonerscited by 16
  2. 2025Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?cited by 12
  3. 2026Understanding Multilingualism in Mixture-of-Experts LLMs: Routing Mechanism, Expert Specialization, and Layerwise Steeringcited by 10
  4. 2025Language Specific Knowledge: Do Models Know Better in X than in English?cited by 4
  5. 2026Language of Thought Shapes Output Diversity in Large Language Modelscited by 4
  6. 2026What Makes Good Multilingual Reasoning? Disentangling Traces with Measurable Featurescited by 4
  7. 2025EfficientXLang: Towards Improving Token Efficiency Through Cross-Lingual Reasoningcited by 3
  8. 2026Abstract Activation Spaces for Content-Invariant Reasoning in Large Language Modelscited by 3
  9. 2026Cross-lingual Self-Consistency for Multilingual Reasoning with Language Modelscited by 3
  10. 2026Med-CoReasoner: Reducing Language Disparities in Medical Reasoning via Language-Informed Co-Reasoningcited by 2
  11. 2026Think Multilingual, Not Harder: A Data-Efficient Framework for Teaching Reasoning Models to Code-Switchcited by 2
  12. 2026Language as a Latent Variable for Reasoning Optimizationcited by 2
4 more
  1. 2025LLaMAX2: Your Translation-Enhanced Model also Performs Well in Reasoningcited by 1
  2. 2026Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generationcited by 1
  3. 2026AdaMame: A Training Recipe for Adaptive Multilingual Reasoningcited by 0
  4. 2026Do LLM Debates Repeat Arguments Differently Across Languages?cited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Rethinking the Multilingual Reasoning Gap with Layer Swap
  2. 2025MultiNRC: A Challenging and Native Multilingual Reasoning Evaluation Benchmark for LLMs
  3. 2025The Reasoning Lingua Franca: A Double-Edged Sword for Multilingual AI
  4. 2025A Survey of Multilingual Reasoning in Language Models
  5. 2025Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models?
  6. 2025Best-of-L: Cross-Lingual Reward Modeling for Mathematical Reasoning
  7. 2024Eliciting Better Multilingual Structured Reasoning from LLMs through Code
  8. 2025Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning