# Cultural Alignment in Large Language Models Using Soft Prompt Tuning

arXiv: https://arxiv.org/abs/2503.16094 · HTML: https://mlsanity.com/paper/2503.16094/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 26 of its 57 references that are in the map.
- First posted on arXiv 20 Mar 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [The CMA Evolution Strategy: A Tutorial](https://mlsanity.com/paper/1604.00772/) (2016)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [A Roadmap to Pluralistic Alignment](https://mlsanity.com/paper/2402.05070/) (2024)
- [Probing Pre-Trained Language Models for Cross-Cultural Differences in Values](https://mlsanity.com/paper/2203.13722/) (2022)
- [The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models](https://mlsanity.com/paper/2404.16019/) (2024)
- [Theoretical guarantees on the best-of-n alignment policy](https://mlsanity.com/paper/2401.01879/) (2024)
- [Black-Box Prompt Optimization: Aligning Large Language Models without Model Training](https://mlsanity.com/paper/2311.04155/) (2023)
- [Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions](https://mlsanity.com/paper/2309.12342/) (2023)
- [SeaLLMs -- Large Language Models for Southeast Asia](https://mlsanity.com/paper/2312.00738/) (2023)
- [Survey of Cultural Awareness in Language Models: Text and Beyond](https://mlsanity.com/paper/2411.00860/) (2024)
- [AceGPT, Localizing Large Language Models in Arabic](https://mlsanity.com/paper/2309.12053/) (2023)
- [COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning](https://mlsanity.com/paper/2403.18058/) (2024)
- [Cendol: Open Instruction-tuned Generative Large Language Models for Indonesian Languages](https://mlsanity.com/paper/2404.06138/) (2024)
- [UCCIX: Irish-eXcellence Large Language Model](https://mlsanity.com/paper/2405.13010/) (2024)

## Built on by (most cited first, 5 of 5)

- [A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus in LLMs](https://mlsanity.com/paper/2506.13245/) (2025)
- [Whispers of Many Shores: Cultural Alignment through Collaborative Cultural Expertise](https://mlsanity.com/paper/2506.00242/) (2025)
- ['Too much alignment; not enough culture': Re-balancing cultural alignment practices in LLMs](https://mlsanity.com/paper/2509.26167/) (2025)
- [CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia](https://mlsanity.com/paper/2608.28405/) (2026)
- [Demographic Pluralism: Inference-Time Modeling of Pluralistic Human Preference Distributions](https://mlsanity.com/paper/2609.38555/) (2026)

## Abstract (arXiv)

Large Language Model (LLM) alignment is commonly achieved through supervised fine-tuning or reinforcement learning, both of which require labeled or preference data and update model weights. Without targeted cultural adaptation, however, deployed LLMs often exhibit culturally homogeneous behavior that fails to reflect diverse local values. Aligning models to cultural value frameworks such as Hofstede's Value Survey Module (VSM13) presents a distinct challenge: alignment signals are available only as aggregated survey-level scores computed after generating responses to an entire survey, providing no per-token gradient and requiring no preference data by construction. This makes standard gradient-based alignment methods ill-suited to the task. We propose a deployment-friendly approach that encodes cultural behavior in short, tunable soft prompts optimized with Differential Evolution (DE), while keeping model weights frozen and requiring no preference data. At inference, the system inserts the appropriate cultural-specific prompt to adapt model responses for different cultures. Experiments across four countries and four instruction-tuned models show that DE-optimized prompts generally reduce discrepancy with VSM13 reference profiles, improve rank agreement with the World Values Survey (WVS), an independent framework not seen during optimization, and are preferred in blinded pairwise evaluations using majority voting across three LLM judges.