# Self-Pluralising Culture Alignment for Large Language Models

arXiv: https://arxiv.org/abs/2410.12971 · HTML: https://mlsanity.com/paper/2410.12971/

## Key facts

- Cited by 31 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 31 of its 45 references that are in the map.
- First posted on arXiv 16 Oct 2024.

## 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, 30 of 31)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Large Language Model Alignment: A Survey](https://mlsanity.com/paper/2309.15025/) (2023)
- [Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias](https://mlsanity.com/paper/2306.15895/) (2023)
- [Challenges and Strategies in Cross-Cultural NLP](https://mlsanity.com/paper/2203.10020/) (2022)
- [Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study](https://mlsanity.com/paper/2303.17466/) (2023)
- [Evaluating Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2310.19736/) (2023)
- [Probing Pre-Trained Language Models for Cross-Cultural Differences in Values](https://mlsanity.com/paper/2203.13722/) (2022)
- [Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration](https://mlsanity.com/paper/2406.15951/) (2024)
- [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)
- [Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback](https://mlsanity.com/paper/2404.10271/) (2024)
- [Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models](https://mlsanity.com/paper/2402.13064/) (2024)
- [AceGPT, Localizing Large Language Models in Arabic](https://mlsanity.com/paper/2309.12053/) (2023)
- [Unintended Impacts of LLM Alignment on Global Representation](https://mlsanity.com/paper/2402.15018/) (2024)
- [Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting](https://mlsanity.com/paper/2310.16523/) (2023)
- [Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models](https://mlsanity.com/paper/2310.12481/) (2023)
- [SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning](https://mlsanity.com/paper/2407.12874/) (2024)
- [Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?](https://mlsanity.com/paper/2402.18120/) (2024)
- [Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learning](https://mlsanity.com/paper/2408.16482/) (2024)
- [The Myth of Culturally Agnostic AI Models](https://mlsanity.com/paper/2211.15271/) (2022)
- [The Echoes of Multilinguality: Tracing Cultural Value Shifts during LM Fine-tuning](https://mlsanity.com/paper/2405.12744/) (2024)

## Built on by (most cited first, 30 of 31)

- [Multilingual Large Language Models: A Systematic Survey](https://mlsanity.com/paper/2411.11072/) (2024)
- [Cultural Palette: Pluralising Culture Alignment via Multi-agent Palette](https://mlsanity.com/paper/2412.11167/) (2024)
- [CARE: Multilingual Human Preference Learning for Cultural Awareness](https://mlsanity.com/paper/2504.05154/) (2025)
- [From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMs](https://mlsanity.com/paper/2505.16408/) (2025)
- [CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimization](https://mlsanity.com/paper/2504.08820/) (2025)
- [Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives](https://mlsanity.com/paper/2506.09656/) (2025)
- [Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models](https://mlsanity.com/paper/2510.18526/) (2025)
- [Zhyper: Factorized Hypernetworks for Conditioned LLM Fine-Tuning](https://mlsanity.com/paper/2510.19733/) (2025)
- [Long-Tail Knowledge in Large Language Models: Taxonomy, Mechanisms, Interventions and Implications](https://mlsanity.com/paper/2602.16201/) (2026)
- [MAD-Fact: A Multi-Agent Debate Framework for Long-Form Factuality Evaluation in LLMs](https://mlsanity.com/paper/2510.22967/) (2025)
- [Language of Thought Shapes Output Diversity in Large Language Models](https://mlsanity.com/paper/2601.11227/) (2026)
- [Mind the Gap in Cultural Alignment: Task-Aware Culture Management for Large Language Models](https://mlsanity.com/paper/2602.22475/) (2026)
- [From Word to World: Evaluate and Mitigate Culture Bias in LLMs via Word Association Test](https://mlsanity.com/paper/2505.18562/) (2025)
- [Neuron-Level Analysis of Cultural Understanding in Large Language Models](https://mlsanity.com/paper/2510.08284/) (2025)
- [Overton Pluralistic Reinforcement Learning for Large Language Models](https://mlsanity.com/paper/2602.20759/) (2026)
- [Cultural Authenticity: Comparing LLM Cultural Representations to Native Human Expectations](https://mlsanity.com/paper/2604.03493/) (2026)
- [ValueGround: Evaluating Culture-Conditioned Visual Value Grounding in MLLMs](https://mlsanity.com/paper/2604.06484/) (2026)
- [Jailbreaking Large Language Models with Morality Attacks](https://mlsanity.com/paper/2604.17053/) (2026)
- [DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping](https://mlsanity.com/paper/2605.14420/) (2026)
- [PLURAL: A Global Dataset for Value Alignment](https://mlsanity.com/paper/2607.08034/) (2026)
- [Reasoning Shapes Alignment: Investigating Cultural Alignment in Large Reasoning Models with Cultural Norms](https://mlsanity.com/paper/2511.13359/) (2025)
- [From National Curricula to Cultural Awareness: Constructing Open-Ended Culture-Specific Question Answering Dataset](https://mlsanity.com/paper/2601.04632/) (2026)
- [CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters](https://mlsanity.com/paper/2601.04885/) (2026)
- [Toward Culturally Grounded Natural Language Processing](https://mlsanity.com/paper/2603.26013/) (2026)
- [C-Mining: Unsupervised Discovery of Seeds for Cultural Data Synthesis via Geometric Misalignment](https://mlsanity.com/paper/2604.15675/) (2026)
- [Jupiter-N Technical Report](https://mlsanity.com/paper/2604.17429/) (2026)
- [Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems](https://mlsanity.com/paper/2606.05985/) (2026)
- [MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning](https://mlsanity.com/paper/2607.11736/) (2026)
- [Where Models Converge and Humans Diverge: A Coverage Framework for Distributional Pluralism in Open-Ended Generation](https://mlsanity.com/paper/2608.05576/) (2026)
- [ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Models](https://mlsanity.com/paper/2608.20355/) (2026)

## Abstract (arXiv)

As large language models (LLMs) become increasingly accessible in many countries, it is essential to align them to serve pluralistic human values across cultures. However, pluralistic culture alignment in LLMs remain an open problem. In this paper, we propose CultureSPA, a Self-Pluralising Culture Alignment framework that allows LLMs to simultaneously align to pluralistic cultures. The framework first generates questions on various culture topics, then yields LLM outputs in response to these generated questions under both culture-aware and culture-unaware settings. By comparing culture-aware/unaware outputs, we are able to detect and collect culture-related instances. These instances are employed to fine-tune LLMs to serve pluralistic cultures in either a culture-joint or culture-specific way. Extensive experiments demonstrate that CultureSPA significantly improves the alignment of LLMs to diverse cultures without compromising general abilities. And further improvements can be achieved if CultureSPA is combined with advanced prompt engineering techniques. Comparisons between culture-joint and culture-specific tuning strategies, along with variations in data quality and quantity, illustrate the robustness of our method. We also explore the mechanisms underlying CultureSPA and the relations between different cultures it reflects.