mlsanityData to 14 Oct 2026

Meta-Cultural Competence: Climbing the Right Hill of Cultural Awareness

arXiv 2502.09637 ↗First posted 9 Feb 2025cs.CY cs.AI cs.CLcited by 8

Not on the map. Why?

Abstract (arXiv)

Numerous recent studies have shown that Large Language Models (LLMs) are biased towards a Western and Anglo-centric worldview, which compromises their usefulness in non-Western cultural settings. However, "culture" is a complex, multifaceted topic, and its awareness, representation, and modeling in LLMs and LLM-based applications can be defined and measured in numerous ways. In this position paper, we ask what does it mean for an LLM to possess "cultural awareness", and through a thought experiment, which is an extension of the Octopus test proposed by Bender and Koller (2020), we argue that it is not cultural awareness or knowledge, rather meta-cultural competence, which is required of an LLM and LLM-based AI system that will make it useful across various, including completely unseen, cultures. We lay out the principles of meta-cultural competence AI systems, and discuss ways to measure and model those.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 52 of its 140 references that are in the map. First posted on arXiv 9 Feb 2025.

Builds on

52 of 140 references.

References · 52

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2019Language Models as Knowledge Bases?cited by 1,936
  3. 2019Cross-lingual Language Model Pretrainingcited by 1,090
  4. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  5. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 924
  6. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 817
  7. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 759
  8. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 719
  9. 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 710
  10. 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 653
  11. 2024Large Language Models: A Surveycited by 525
  12. 2019Introduction to Multi-Armed Banditscited by 481
38 more
  1. 2023A Survey of Hallucination in Large Foundation Modelscited by 368
  2. 2024Break the Sequential Dependency of LLM Inference Using Lookahead Decodingcited by 298
  3. 2023Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Studycited by 206
  4. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  5. 2024BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languagescited by 173
  6. 2019Evaluating model calibration in classificationcited by 168
  7. 2024Towards Measuring and Modeling "Culture" in LLMs: A Surveycited by 167
  8. 2022A Survey on Retrieval-Augmented Text Generationcited by 158
  9. 2020Continual Lifelong Learning in Natural Language Processing: A Surveycited by 152
  10. 2023KoBBQ: Korean Bias Benchmark for Question Answeringcited by 71
  11. 2024A Complete Survey on LLM-based AI Chatbotscited by 71
  12. 2023SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Modelscited by 66
  13. 2023Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMscited by 64
  14. 2024AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuancescited by 60
  15. 2019How should my chatbot interact? A survey on human-chatbot interaction designcited by 56
  16. 2024CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Promptingcited by 55
  17. 2023Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLUcited by 53
  18. 2024How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensionscited by 52
  19. 2023Large Language Models as Superpositions of Cultural Perspectivescited by 49
  20. 2024Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them incited by 46
  21. 2023Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decodingcited by 40
  22. 2020Meta-learning in natural and artificial intelligencecited by 39
  23. 2024IndoCulture: Exploring Geographically-Influenced Cultural Commonsense Reasoning Across Eleven Indonesian Provincescited by 39
  24. 2023Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systemscited by 37
  25. 2024Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanesecited by 36
  26. 2023COPAL-ID: Indonesian Language Reasoning with Local Culture and Nuancescited by 35
  27. 2024Does Mapo Tofu Contain Coffee? Probing LLMs for Food-related Cultural Knowledgecited by 29
  28. 2024Large Language Models as Recommender Systems: A Study of Popularity Biascited by 26
  29. 2023Probing the Moral Development of Large Language Models through Defining Issues Testcited by 25
  30. 2024"They are uncultured": Unveiling Covert Harms and Social Threats in LLM Generated Conversationscited by 25
  31. 2024DOSA: A Dataset of Social Artifacts from Different Indian Geographical Subculturescited by 24
  32. 2023CDEval: A Benchmark for Measuring the Cultural Dimensions of Large Language Modelscited by 23
  33. 2024Cultural Conditioning or Placebo? On the Effectiveness of Socio-Demographic Promptingcited by 22
  34. 2024The Sociolinguistic Foundations of Language Modelingcited by 13
  35. 2024Komodo: A Linguistic Expedition into Indonesia's Regional Languagescited by 10
  36. 2023CreoleVal: Multilingual Multitask Benchmarks for Creolescited by 9
  37. 2024Evaluating Cultural Awareness of LLMs for Yoruba, Malayalam, and Englishcited by 8
  38. 2024Analyzing Cultural Representations of Emotions in LLMs through Mixed Emotion Surveycited by 7

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 3.

8 papers.

  1. 2025Fluent but Foreign: Even Regional LLMs Lack Cultural Alignmentcited by 10
  2. 2025Meaning Is Not A Metric: Using LLMs to make cultural context legible at scalecited by 10
  3. 2025When Cultures Meet: Multicultural Text-to-Image Generationcited by 7
  4. 2025Is It Bad to Work All the Time? Cross-Cultural Evaluation of Social Norm Biases in GPT-4cited by 5
  5. 2025Can LLMs Grasp Implicit Cultural Values? Benchmarking LLMs' Cultural Intelligence with CQ-Benchcited by 3
  6. 2026Defining Cultural Capabilities for AI Evaluation: A Taxonomy Grounded in Intercultural Communication Theorycited by 1
  7. 2026To Generate or Discriminate? Methodological Considerations for Measuring Cultural Alignment in LLMscited by 0
  8. 2026C-Mining: Unsupervised Discovery of Seeds for Cultural Data Synthesis via Geometric Misalignmentcited by 0