# CultureLLM: Incorporating Cultural Differences into Large Language Models

arXiv: https://arxiv.org/abs/2402.10946 · HTML: https://mlsanity.com/paper/2402.10946/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 90 references that are in the map.
- First posted on arXiv 9 Feb 2024.

## Builds on (most cited first, 30 of 51)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models](https://mlsanity.com/paper/2309.12284/) (2023)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)
- [Improving Text Embeddings with Large Language Models](https://mlsanity.com/paper/2401.00368/) (2023)
- [MEGA: Multilingual Evaluation of Generative AI](https://mlsanity.com/paper/2303.12528/) (2023)
- [AI Alignment: A Comprehensive Survey](https://mlsanity.com/paper/2310.19852/) (2023)
- [Large Language Model Alignment: A Survey](https://mlsanity.com/paper/2309.15025/) (2023)
- [Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study](https://mlsanity.com/paper/2303.17466/) (2023)
- [Having Beer after Prayer? Measuring Cultural Bias in Large Language Models](https://mlsanity.com/paper/2305.14456/) (2023)
- [Self-Alignment with Instruction Backtranslation](https://mlsanity.com/paper/2308.06259/) (2023)
- [SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)](https://mlsanity.com/paper/2006.07235/) (2020)
- [Multilingual and Multi-Aspect Hate Speech Analysis](https://mlsanity.com/paper/1908.11049/) (2019)
- [Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions](https://mlsanity.com/paper/2309.12342/) (2023)
- [The Ghost in the Machine has an American accent: value conflict in GPT-3](https://mlsanity.com/paper/2203.07785/) (2022)
- [SeaLLMs -- Large Language Models for Southeast Asia](https://mlsanity.com/paper/2312.00738/) (2023)
- [Measuring the Reliability of Hate Speech Annotations: The Case of the European Refugee Crisis](https://mlsanity.com/paper/1701.08118/) (2017)
- [CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility](https://mlsanity.com/paper/2307.09705/) (2023)
- [Better to Ask in English: Cross-Lingual Evaluation of Large Language Models for Healthcare Queries](https://mlsanity.com/paper/2310.13132/) (2023)
- [Extracting Cultural Commonsense Knowledge at Scale](https://mlsanity.com/paper/2210.07763/) (2022)
- [TinyGSM: achieving >80% on GSM8k with small language models](https://mlsanity.com/paper/2312.09241/) (2023)
- [Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs](https://mlsanity.com/paper/2310.07251/) (2023)
- [Making Large Language Models Better Reasoners with Alignment](https://mlsanity.com/paper/2309.02144/) (2023)
- [SOLID: A Large-Scale Semi-Supervised Dataset for Offensive Language Identification](https://mlsanity.com/paper/2004.14454/) (2020)
- [Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models](https://mlsanity.com/paper/2206.09917/) (2022)
- [Offensive Language Identification in Greek](https://mlsanity.com/paper/2003.07459/) (2020)

## Built on by (most cited first, 30 of 50)

- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [Survey of Cultural Awareness in Language Models: Text and Beyond](https://mlsanity.com/paper/2411.00860/) (2024)
- [On the Diversity of Synthetic Data and its Impact on Training Large Language Models](https://mlsanity.com/paper/2410.15226/) (2024)
- [CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting](https://mlsanity.com/paper/2404.10199/) (2024)
- [CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 Countries](https://mlsanity.com/paper/2501.01282/) (2025)
- [Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements](https://mlsanity.com/paper/2410.08968/) (2024)
- [CulturalTeaming: AI-Assisted Interactive Red-Teaming for Challenging LLMs' (Lack of) Multicultural Knowledge](https://mlsanity.com/paper/2404.06664/) (2024)
- [Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research](https://mlsanity.com/paper/2412.04497/) (2024)
- [Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art](https://mlsanity.com/paper/2406.03930/) (2024)
- [CulturePark: Boosting Cross-cultural Understanding in Large Language Models](https://mlsanity.com/paper/2405.15145/) (2024)
- [Eureka: Evaluating and Understanding Large Foundation Models](https://mlsanity.com/paper/2409.10566/) (2024)
- [Multilingual Large Language Models: A Systematic Survey](https://mlsanity.com/paper/2411.11072/) (2024)
- [Stick to your Role! Stability of Personal Values Expressed in Large Language Models](https://mlsanity.com/paper/2402.14846/) (2024)
- [ChatNVD: Advancing Cybersecurity Vulnerability Assessment with Large Language Models](https://mlsanity.com/paper/2412.04756/) (2024)
- [ValuesRAG: Enhancing Cultural Alignment Through Retrieval-Augmented Contextual Learning](https://mlsanity.com/paper/2501.01031/) (2025)
- [Fleming-R1: Toward Expert-Level Medical Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2509.15279/) (2025)
- [From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMs](https://mlsanity.com/paper/2505.16408/) (2025)
- [On Fairness of Unified Multimodal Large Language Model for Image Generation](https://mlsanity.com/paper/2502.03429/) (2025)
- [Foundation Models for Low-Resource Language Education (Vision Paper)](https://mlsanity.com/paper/2412.04774/) (2024)
- [Building Benchmarks from the Ground Up: Community-Centered Evaluation of LLMs in Healthcare Chatbot Settings](https://mlsanity.com/paper/2509.24506/) (2025)
- [Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models](https://mlsanity.com/paper/2510.18526/) (2025)
- [Through the Prism of Culture: Evaluating LLMs' Understanding of Indian Subcultures and Traditions](https://mlsanity.com/paper/2501.16748/) (2025)
- [Fair-PP: A Synthetic Dataset for Aligning LLM with Personalized Preferences of Social Equity](https://mlsanity.com/paper/2505.11861/) (2025)
- [Embodied AI with Foundation Models for Mobile Service Robots: A Systematic Review](https://mlsanity.com/paper/2505.20503/) (2025)
- [MCEval: A Dynamic Framework for Fair Multilingual Cultural Evaluation of LLMs](https://mlsanity.com/paper/2507.09701/) (2025)
- [Communicate to Play: Pragmatic Reasoning for Efficient Cross-Cultural Communication in Codenames](https://mlsanity.com/paper/2408.04900/) (2024)
- [Node Importance Estimation Leveraging LLMs for Semantic Augmentation in Knowledge Graphs](https://mlsanity.com/paper/2412.00478/) (2024)
- [Exploring Cross-lingual Latent Transplantation: Mutual Opportunities and Open Challenges](https://mlsanity.com/paper/2412.12686/) (2024)
- [When LLMs Team Up: The Emergence of Collaborative Affective Computing](https://mlsanity.com/paper/2506.01698/) (2025)
- [Tailored untruths: How personalisation challenges LLM safeguards](https://mlsanity.com/paper/2510.12993/) (2025)

## Abstract (arXiv)

Large language models (LLMs) are reported to be partial to certain cultures owing to the training data dominance from the English corpora. Since multilingual cultural data are often expensive to collect, existing efforts handle this by prompt engineering or culture-specific pre-training. However, they might overlook the knowledge deficiency of low-resource culture and require extensive computing resources. In this paper, we propose CultureLLM, a cost-effective solution to incorporate cultural differences into LLMs. CultureLLM adopts World Value Survey (WVS) as seed data and generates semantically equivalent training data via the proposed semantic data augmentation. Using only 50 seed samples from WVS with augmented data, we fine-tune culture-specific LLMs and one unified model (CultureLLM-One) for 9 cultures covering rich and low-resource languages. Extensive experiments on 60 culture-related datasets demonstrate that CultureLLM significantly outperforms various counterparts such as GPT-3.5 (by 8.1%) and Gemini Pro (by 9.5%) with comparable performance to GPT-4 or even better. Our human study shows that the generated samples are semantically equivalent to the original samples, providing an effective solution for LLMs augmentation. Code is released at https://github.com/Scarelette/CultureLLM.