mlsanityData to 7 Oct 2026

Self-Pluralising Culture Alignment for Large Language Models

arXiv 2410.12971 ↗First posted 16 Oct 2024cs.CLcited by 31

On the map: LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment

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.

Key facts. Cited by 31 papers in the map (data through 7 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.

Builds on

31 of 45 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learning29 Aug
  2. 2024Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration22 Jun
  3. 2024Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback16 Apr
  4. 2024Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?28 Feb
  5. 2023AceGPT, Localizing Large Language Models in Arabic21 Sep

Other references · 26

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  5. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  6. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  7. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  8. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  9. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,968
  10. 2023LIMA: Less Is More for Alignmentcited by 1,080
  11. 2023Large Language Model Alignment: A Surveycited by 241
  12. 2023Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Biascited by 230
14 more
  1. 2022Challenges and Strategies in Cross-Cultural NLPcited by 216
  2. 2023Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Studycited by 203
  3. 2023Evaluating Large Language Models: A Comprehensive Surveycited by 200
  4. 2022Probing Pre-Trained Language Models for Cross-Cultural Differences in Valuescited by 147
  5. 2023Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensionscited by 111
  6. 2023SeaLLMs -- Large Language Models for Southeast Asiacited by 104
  7. 2024Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Modelscited by 99
  8. 2024Unintended Impacts of LLM Alignment on Global Representationcited by 66
  9. 2023Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Votingcited by 46
  10. 2023Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Modelscited by 42
  11. 2024SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuningcited by 32
  12. 2022The Myth of Culturally Agnostic AI Modelscited by 11
  13. 2024The Echoes of Multilinguality: Tracing Cultural Value Shifts during LM Fine-tuningcited by 10
  14. 2024FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Datacited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 10; 2026: 19.

31 papers.

Sort:

By area:

  1. 2024Multilingual Large Language Models: A Systematic Surveycited by 18
  2. 2025CARE: Multilingual Human Preference Learning for Cultural Awarenesscited by 15
  3. 2024Cultural Palette: Pluralising Culture Alignment via Multi-agent Palettecited by 14
  4. 2025From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMscited by 9
  5. 2025CAReDiO: Cultural Alignment via Representativeness and Distinctiveness Guided Data Optimizationcited by 5
  6. 2025Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Modelscited by 5
  7. 2025Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectivescited by 4
  8. 2025MAD-Fact: A Multi-Agent Debate Framework for Long-Form Factuality Evaluation in LLMscited by 4
  9. 2025Zhyper: Factorized Hypernetworks for Conditioned LLM Fine-Tuningcited by 3
  10. 2026Language of Thought Shapes Output Diversity in Large Language Modelscited by 3
  11. 2026Mind the Gap in Cultural Alignment: Task-Aware Culture Management for Large Language Modelscited by 3
  12. 2025From Word to World: Evaluate and Mitigate Culture Bias in LLMs via Word Association Testcited by 2
19 more
  1. 2026Long-Tail Knowledge in Large Language Models: Taxonomy, Mechanisms, Interventions and Implicationscited by 2
  2. 2025Neuron-Level Analysis of Cultural Understanding in Large Language Modelscited by 1
  3. 2026Overton Pluralistic Reinforcement Learning for Large Language Modelscited by 1
  4. 2026Cultural Authenticity: Comparing LLM Cultural Representations to Native Human Expectationscited by 1
  5. 2026ValueGround: Evaluating Culture-Conditioned Visual Value Grounding in MLLMscited by 1
  6. 2026Jailbreaking Large Language Models with Morality Attackscited by 1
  7. 2026DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mappingcited by 1
  8. 2026PLURAL: A Global Dataset for Value Alignmentcited by 1
  9. 2025Reasoning Shapes Alignment: Investigating Cultural Alignment in Large Reasoning Models with Cultural Normscited by 0
  10. 2026From National Curricula to Cultural Awareness: Constructing Open-Ended Culture-Specific Question Answering Datasetcited by 0
  11. 2026CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapterscited by 0
  12. 2026Toward Culturally Grounded Natural Language Processingcited by 0
  13. 2026C-Mining: Unsupervised Discovery of Seeds for Cultural Data Synthesis via Geometric Misalignmentcited by 0
  14. 2026Jupiter-N Technical Reportcited by 0
  15. 2026Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systemscited by 0
  16. 2026MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoningcited by 0
  17. 2026Where Models Converge and Humans Diverge: A Coverage Framework for Distributional Pluralism in Open-Ended Generationcited by 0
  18. 2026ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Modelscited by 0
  19. 2026PlurVA-LLM-2026 Shared Task Track-1: Pluralistic Value Alignment in LLMs via Multilingual Fine-Tuning and Threshold Calibrationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Aligned but Flattened: Analyzing the Trade-off between Cultural Alignment and Diversity in LLMs
  2. 2026AlignCultura: Towards Culturally Aligned Large Language Models?
  3. 2026Cross-Lingual Consensus: Aligning Multilingual Cultural Knowledge via Multilingual Self-Consistency
  4. 2023CDEval: A Benchmark for Measuring the Cultural Dimensions of Large Language Models
  5. 2025Whispers of Many Shores: Cultural Alignment through Collaborative Cultural Expertise
  6. 2025CulFiT: A Fine-grained Cultural-aware LLM Training Paradigm via Multilingual Critique Data Synthesis
  7. 2025Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMs
  8. 2025Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs