# Language of Thought Shapes Output Diversity in Large Language Models

arXiv: https://arxiv.org/abs/2601.11227 · HTML: https://mlsanity.com/paper/2601.11227/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 40 of its 47 references that are in the map.
- First posted on arXiv 16 Jan 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 40)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [Texygen: A Benchmarking Platform for Text Generation Models](https://mlsanity.com/paper/1802.01886/) (2018)
- [Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study](https://mlsanity.com/paper/2303.17466/) (2023)
- [BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages](https://mlsanity.com/paper/2406.09948/) (2024)
- [How do Large Language Models Handle Multilingualism?](https://mlsanity.com/paper/2402.18815/) (2024)
- [Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)](https://mlsanity.com/paper/2510.22954/) (2025)
- [Evaluating the Evaluation of Diversity in Natural Language Generation](https://mlsanity.com/paper/2004.02990/) (2020)
- [Mapping the Increasing Use of LLMs in Scientific Papers](https://mlsanity.com/paper/2404.01268/) (2024)
- [The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text](https://mlsanity.com/paper/2311.09807/) (2023)
- [Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback](https://mlsanity.com/paper/2404.10271/) (2024)
- [Is Temperature the Creativity Parameter of Large Language Models?](https://mlsanity.com/paper/2405.00492/) (2024)
- [Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?](https://mlsanity.com/paper/2502.12215/) (2025)
- [NoveltyBench: Evaluating Language Models for Humanlike Diversity](https://mlsanity.com/paper/2504.05228/) (2025)
- [PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts](https://mlsanity.com/paper/2504.18428/) (2025)
- [Crosslingual Reasoning through Test-Time Scaling](https://mlsanity.com/paper/2505.05408/) (2025)
- [Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models](https://mlsanity.com/paper/2310.12481/) (2023)
- [LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity](https://mlsanity.com/paper/2410.03953/) (2024)
- [Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning](https://mlsanity.com/paper/2502.17407/) (2025)
- [SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages](https://mlsanity.com/paper/2407.19672/) (2024)
- [Self-Pluralising Culture Alignment for Large Language Models](https://mlsanity.com/paper/2410.12971/) (2024)
- [Multilingual Prompting for Improving LLM Generation Diversity](https://mlsanity.com/paper/2505.15229/) (2025)
- [Modeling Human Subjectivity in LLMs Using Explicit and Implicit Human Factors in Personas](https://mlsanity.com/paper/2406.14462/) (2024)
- [IdeaBench: Benchmarking Large Language Models for Research Idea Generation](https://mlsanity.com/paper/2411.02429/) (2024)
- [The Emergence of Abstract Thought in Large Language Models Beyond Any Language](https://mlsanity.com/paper/2506.09890/) (2025)
- [Babel: Open Multilingual Large Language Models Serving Over 90% of Global Speakers](https://mlsanity.com/paper/2503.00865/) (2025)
- [Could Thinking Multilingually Empower LLM Reasoning?](https://mlsanity.com/paper/2504.11833/) (2025)
- [When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners](https://mlsanity.com/paper/2505.15257/) (2025)
- [Disentangling Language and Culture for Evaluating Multilingual Large Language Models](https://mlsanity.com/paper/2505.24635/) (2025)

## Built on by (most cited first, 4 of 4)

- [Language as a Latent Variable for Reasoning Optimization](https://mlsanity.com/paper/2604.21593/) (2026)
- [Multilingual Fine-Tuning via Localized Gradient Conflict Resolution](https://mlsanity.com/paper/2606.05613/) (2026)
- [Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems](https://mlsanity.com/paper/2606.05985/) (2026)
- [PLDiv: Measuring Dataset Diversity and Semantic Collapse via Persistence Landscapes](https://mlsanity.com/paper/2610.14031/) (2026)

## Abstract (arXiv)

Output diversity is crucial for Large Language Models as it underpins pluralism and creativity. In this work, we reveal that controlling the language used during model thinking-the language of thought-provides a novel and structural source of output diversity. Our preliminary study shows that different thinking languages occupy distinct regions in a model's thinking space. Based on this observation, we study two repeated sampling strategies under multilingual thinking-Single-Language Sampling and Mixed-Language Sampling-and conduct diversity evaluation on outputs that are controlled to be in English, regardless of the thinking language used. Across extensive experiments, we demonstrate that switching the thinking language from English to non-English languages consistently increases output diversity, with a clear and consistent positive correlation such that languages farther from English in the thinking space yield larger gains. We further show that aggregating samples across multiple thinking languages yields additional improvements through compositional effects, and that scaling sampling with linguistic heterogeneity expands the model's diversity ceiling. Finally, we show that these findings translate into practical benefits in pluralistic alignment scenarios, leading to broader coverage of cultural knowledge and value orientations in LLM outputs. Our code is publicly available at https://github.com/iNLP-Lab/Multilingual-LoT-Diversity.