mlsanityData to 14 Oct 2026

From National Curricula to Cultural Awareness: Constructing Open-Ended Culture-Specific Question Answering Dataset

arXiv 2601.04632 ↗First posted 8 Jan 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) achieve strong performance on many tasks, but their progress remains uneven across languages and cultures, often reflecting values latent in English-centric training data. To enable practical cultural alignment, we propose a scalable approach that leverages national social studies curricula as a foundation for culture-aware supervision. We introduce CuCu, an automated multi-agent LLM framework that transforms national textbook curricula into open-ended, culture-specific question-answer pairs for supervised fine-tuning (SFT). Applying CuCu to the Korean national social studies curriculum, we construct KCaQA, comprising 34.1k open-ended QA pairs. Our analyses and training experiments suggest that KCaQA covers culture-specific topics and produces responses grounded in local sociocultural contexts.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 53 references that are in the map. First posted on arXiv 8 Jan 2026.

Builds on

32 of 53 references.

References · 32

  1. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  2. 2023LIMA: Less Is More for Alignmentcited by 1,100
  3. 2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 870
  4. 2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 801
  5. 2020Data and its (dis)contents: A survey of dataset development and use in machine learning researchcited by 260
  6. 2022CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Taskcited by 207
  7. 2024Large Language Models for Data Annotation and Synthesis: A Surveycited by 205
  8. 2019Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasetscited by 175
  9. 2024BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languagescited by 173
  10. 2024Investigating Cultural Alignment of Large Language Modelscited by 143
  11. 2023Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensionscited by 112
  12. 2024CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologiescited by 98
20 more
  1. 2024INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledgecited by 86
  2. 2023KoBBQ: Korean Bias Benchmark for Question Answeringcited by 71
  3. 2024CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Koreancited by 66
  4. 2023HAE-RAE Bench: Evaluation of Korean Knowledge in Language Modelscited by 47
  5. 2024CodecLM: Aligning Language Models with Tailored Synthetic Datacited by 39
  6. 2024Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personascited by 37
  7. 2024KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledgecited by 33
  8. 2024Self-Pluralising Culture Alignment for Large Language Modelscited by 31
  9. 2022Discovering Language-neutral Sub-networks in Multilingual Language Modelscited by 28
  10. 2023KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Applicationcited by 24
  11. 2023A Material Lens on Coloniality in NLPcited by 21
  12. 2024Multilingual Large Language Models: A Systematic Surveycited by 18
  13. 2025CARE: Multilingual Human Preference Learning for Cultural Awarenesscited by 15
  14. 2025Do You Know About My Nation? Investigating Multilingual Language Models' Cultural Literacy Through Factual Knowledgecited by 8
  15. 2025Bias in, Bias out: Annotation Bias in Multilingual Large Language Modelscited by 5
  16. 2022KoCHET: a Korean Cultural Heritage corpus for Entity-related Taskscited by 4
  17. 2025Instruction Tuning on Public Government and Cultural Data for Low-Resource Language: a Case Study in Kazakhcited by 4
  18. 2025Pragyaan: Designing and Curating High-Quality Cultural Post-Training Datasets for Indian Languagescited by 3
  19. 2025Hermit Kingdom Through the Lens of Multiple Perspectives: A Case Study of LLM Hallucination on North Koreacited by 2
  20. 2025KoSimpleQA: A Korean Factuality Benchmark with an Analysis of Reasoning LLMscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025CultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer Synthesis
  2. 2025CulFiT: A Fine-grained Cultural-aware LLM Training Paradigm via Multilingual Critique Data Synthesis
  3. 2026No Shortcuts to Culture: Indonesian Multi-hop Question Answering for Complex Cultural Understanding
  4. 2026VIRAASAT: Traversing Novel Paths for Indian Cultural Reasoning
  5. 2024CRAFT: Extracting and Tuning Cultural Instructions from the Wild
  6. 2024CulturalBench: A Robust, Diverse, and Challenging Cultural Benchmark by Human-AI CulturalTeaming
  7. 2025MMA-ASIA: A Multilingual and Multimodal Alignment Framework for Culturally-Grounded Evaluation
  8. 2026MSQA: A Natively Sourced Multilingual and Multicultural SimpleQA Benchmark