# Multilingual Prompting for Improving LLM Generation Diversity

arXiv: https://arxiv.org/abs/2505.15229 · HTML: https://mlsanity.com/paper/2505.15229/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 36 references that are in the map.
- First posted on arXiv 21 May 2025.

## Builds on (most cited first, 18 of 18)

- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Language Models are Multilingual Chain-of-Thought Reasoners](https://mlsanity.com/paper/2210.03057/) (2022)
- [Social Chemistry 101: Learning to Reason about Social and Moral Norms](https://mlsanity.com/paper/2011.00620/) (2020)
- [Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models](https://mlsanity.com/paper/2305.18189/) (2023)
- [Does Writing with Language Models Reduce Content Diversity?](https://mlsanity.com/paper/2309.05196/) (2023)
- [Large language models that replace human participants can harmfully misportray and flatten identity groups](https://mlsanity.com/paper/2402.01908/) (2024)
- [Evaluating the Evaluation of Diversity in Natural Language Generation](https://mlsanity.com/paper/2004.02990/) (2020)
- [Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions](https://mlsanity.com/paper/2306.04140/) (2023)
- [A Note on Shumailov et al. (2024): `AI Models Collapse When Trained on Recursively Generated Data'](https://mlsanity.com/paper/2410.12954/) (2024)
- [Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?](https://mlsanity.com/paper/2211.13972/) (2022)
- [Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting](https://mlsanity.com/paper/2309.07034/) (2023)
- [Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting](https://mlsanity.com/paper/2310.16523/) (2023)
- [Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personas](https://mlsanity.com/paper/2408.06929/) (2024)
- [Cultural Conditioning or Placebo? On the Effectiveness of Socio-Demographic Prompting](https://mlsanity.com/paper/2406.11661/) (2024)
- [Separating form and meaning: Using self-consistency to quantify task understanding across multiple senses](https://mlsanity.com/paper/2305.11662/) (2023)
- [Language Models' Factuality Depends on the Language of Inquiry](https://mlsanity.com/paper/2502.17955/) (2025)

## Built on by (most cited first, 25 of 25)

- [The Homogenizing Effect of Large Language Models on Human Expression and Thought](https://mlsanity.com/paper/2508.01491/) (2025)
- [What and Whose Knowledge? Measuring Epistemic Diversity in Large Language Models](https://mlsanity.com/paper/2510.04226/) (2025)
- [Optimizing Diversity and Quality through Base-Aligned Model Collaboration](https://mlsanity.com/paper/2511.05650/) (2025)
- [CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Models](https://mlsanity.com/paper/2512.07890/) (2025)
- [ConlangCrafter: Constructing Languages with a Multi-Hop LLM Pipeline](https://mlsanity.com/paper/2508.06094/) (2025)
- [Language of Thought Shapes Output Diversity in Large Language Models](https://mlsanity.com/paper/2601.11227/) (2026)
- [Steering LLMs for Culturally Localized Generation](https://mlsanity.com/paper/2603.23301/) (2026)
- [Addressing LLM Diversity by Infusing Random Concepts](https://mlsanity.com/paper/2601.18053/) (2026)
- [Camellia: Benchmarking Cultural Biases in LLMs for Asian Languages](https://mlsanity.com/paper/2510.05291/) (2025)
- [No Single Best Model for Diversity: Learning a Router for Sample Diversity](https://mlsanity.com/paper/2604.02319/) (2026)
- [Exploring the Capability Boundaries of LLMs in Mastering of Chinese Chouxiang Language](https://mlsanity.com/paper/2604.15841/) (2026)
- [Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs](https://mlsanity.com/paper/2605.11128/) (2026)
- [CIEGAD: Cluster-Conditioned Interpolative and Extrapolative Framework for Geometry-Aware and Domain-Aligned Data Augmentation](https://mlsanity.com/paper/2512.10178/) (2025)
- [Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs](https://mlsanity.com/paper/2607.19243/) (2026)
- [Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2609.14896/) (2026)
- [PromptGuard at BLP-2025 Task 1: A Few-Shot Classification Framework Using Majority Voting and Keyword Similarity for Bengali Hate Speech Detection](https://mlsanity.com/paper/2510.09771/) (2025)
- [LLM Jaggedness Unlocks Scientific Creativity](https://mlsanity.com/paper/2605.10574/) (2026)
- [When English Rewrites Local Knowledge: Global Narrative Dominance in Large Language Models](https://mlsanity.com/paper/2605.30481/) (2026)
- [More Is Not More: What Matters for Diversity in LLM Opinions?](https://mlsanity.com/paper/2607.20429/) (2026)
- [Which India Survives Translation? Narrative Homogenisation Across Indian Oral Traditions in LLMs](https://mlsanity.com/paper/2608.26123/) (2026)
- [Personas Differ from Native-Language Generation: Language Pathways Shape LLM Interpersonal Advice](https://mlsanity.com/paper/2608.30873/) (2026)
- [LLMs Mirror Country-Specific Gender Patterns If Asked, but Skew Male When Generating Media in Local Languages](https://mlsanity.com/paper/2609.06545/) (2026)
- [Why Pretraining Fails to Share Cross-Lingual Knowledge](https://mlsanity.com/paper/2609.19291/) (2026)
- [Improving the Diversity of LLM Outputs without a Trade-off](https://mlsanity.com/paper/2609.33038/) (2026)
- [Reach Into The CHOIR: Free-List Elicitation Uncovers Distinct Model Voices in LLM Ensembles](https://mlsanity.com/paper/2609.38448/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are known to lack cultural representation and overall diversity in their generations, from expressing opinions to answering factual questions. To mitigate this problem, we propose multilingual prompting: a prompting method which generates several variations of a base prompt with added cultural and linguistic cues from several cultures, generates responses, and then combines the results. Building on evidence that LLMs have language-specific knowledge, multilingual prompting seeks to increase diversity by activating a broader range of cultural knowledge embedded in model training data. Through experiments across multiple models (GPT-4o, GPT-4o-mini, LLaMA 70B, and LLaMA 8B), we show that multilingual prompting consistently outperforms existing diversity-enhancing techniques such as high-temperature sampling, step-by-step recall, and persona prompting. Further analyses show that the benefits of multilingual prompting vary between high and low resource languages and across model sizes, and that aligning the prompting language with cultural cues reduces hallucination about culturally-specific information.