Cultural Knowledge in Language Models

Follow this topic Ask about this topic

This field studies whether language models can understand and use knowledge tied to particular communities, languages, regions, and historical contexts—not just recall cultural facts. Researchers test this with multilingual question answering, pragmatic dialogue, proverb and metaphor tasks, and cultural-heritage or meme images, often using native-speaker judgments. Methods include retrieval-augmented generation, culturally targeted fine-tuning, activation steering, and mechanistic interpretability. Models often perform unevenly across cultures and languages, and may represent relevant knowledge without applying it; the central challenge is improving cultural grounding without flattening differences or reinforcing stereotypes.

Latest papers

132 papers18 papers in the last four weeks, down 22% on the four weeks before. 0.1% of all new papers.

Evaluating Monolingual and Multilingual Large Language Models for Greek Question Answering: The DemosQA Benchmark
Feb 18, 2026Charalampos Mastrokostas, Nikolaos Giarelis, Nikos KaracapilidisQuestion Answering Multilingual Language Model Evaluation
Industrial Management and Information Systems Lab, MEAD, University of Patras, Rio Patras, Greece
Long-Tail Knowledge in Large Language Models: Taxonomy, Mechanisms, Interventions and Implications
Feb 18, 2026Sanket Badhe, Deep Shah, Nehal KathrotiaFactual Knowledge in Language Models Long-Tail Learning
Google, Mountain View, California, USA
Leveraging Wikidata for Geographically Informed Sociocultural Bias Dataset Creation: Application to Latin America
Feb 16, 2026Yannis Karmim, Renato Pino, Hernan Contreras +6Cultural Bias in Language Models Cultural Knowledge in Language Models
ALMAnaCH · ALMAnaCH team, Inria Paris Center · Dept. of Computer Science, Universidad de Chile +8
The Role of Dataset Linguistic Structure in the Cultural Awareness of Large Language Models
Feb 1, 2026Reem I. Masoud, Chen Feng, Shunta Asano +3LLM Fine-Tuning Cultural Alignment
University College London · King Abdulaziz University · Queen’s University Belfast +3
MasalBench: A Benchmark for Contextual and Cross-Cultural Understanding of Persian Proverbs in LLMs
Jan 29, 2026Ghazal Kalhor, Behnam BahrakCross-Cultural Language Model Evaluation Figurative Language Understanding
School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran · Tehran Institute for Advanced Studies, Khatam University, Tehran, Iran
AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
Jan 25, 2026Xilin Jiang, Qiaolin Wang, Junkai Wu +30Audio-Visual Understanding Multimodal Large Language Models
Columbia University · University of Washington · University of Illinois Urbana-Champaign +5
KoSimpleQA: A Korean Factuality Benchmark with an Analysis of Reasoning LLMs
Oct 21, 2025Donghyeon Ko, Kyubyung Chae, Yeguk Jin +6Multilingual Language Model Evaluation LLM Evaluation
Naver Cloud · Graduate School of Data Science, Seoul National University
The Alignment Veto: How Safety Training Suppresses Cultural Knowledge in LLMs
Oct 15, 2025Pardis Sadat Zahraei, Gokhan Tur, Dilek Hakkani-Tür +1LLM Alignment Refusal Behavior in Language Models
University of Illinois Urbana-Champaign (UIUC) · Qatar Computing Research Institute (QCRI), Hamad Bin Khalifa University
Camellia: Benchmarking Cultural Biases in LLMs for Asian Languages
Oct 6, 2025Tarek Naous, Anagha Savit, Carlos Rafael Catalan +17Multilingual Language Model Evaluation Cultural Bias in Language Models
Georgia Institute of Technology · Samsung R&D Institute Philippines · Sungkyunkwan University +6
How K-12 Teachers Adapt Generative AI to Local Classroom Demands: Cultural Distance Between GenAI Defaults and Everyday Teaching Practices
Sep 13, 2025Qing Xiao, Ruiwei Xiao, Hanqi Jane Li +4Generative AI in Education Generative AI Adoption
Carnegie Mellon University, Pittsburgh, Pennsylvania, USA · University of California, San Diego, La Jolla, California, USA · University of Michigan, Ann Arbor, Michigan, USA
C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models
Jun 2, 2025Ping Wu, Guobin Shen, Dongcheng Zhao +6Value Alignment LLM Alignment
BrainCog Lab, Institute of Automation, Chinese Academy of Sciences, Beijing, China · The School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China · Beijing Key Laboratory of Safe AI and Superalignment, Beijing, China +2
Language Specific Knowledge: Do Models Know Better in X than in English?
May 21, 2025Ishika Agarwal, Nimet Beyza Bozdag, Dilek Hakkani-TürMultilingual Language Models Multilingual QA
Department of Computer Science University of Illinois, Urbana-Champaign

Feb 18, 2026J/K move · Enter open · S save

Evaluating Monolingual and Multilingual Large Language Models for Greek Question Answering: The DemosQA Benchmark

Charalampos Mastrokostas, Nikolaos Giarelis, Nikos Karacapilidis

Industrial Management and Information Systems Lab, MEAD, University of Patras, Rio Patras, Greece

Question Answering Multilingual Language Model Evaluation Low-Resource Language Processing Cultural Knowledge in Language Models

Open paper AskPDF arXiv

Recent advancements in Natural Language Processing and Deep Learning have enabled the development of Large Language Models (LLMs), which have significantly advanced the state-of-the-art across a wide range of tasks, including Question Answering (QA). Despite these advancements, research on LLMs has primarily targeted high-resourced languages (e.g., English), and only recently has attention shifted toward multilingual models. However, these models demonstrate a training data bias towards a small number of popular languages or rely on transfer learning from high- to under-resourced languages; this may lead to a misrepresentation of social, cultural, and historical aspects. To address this challenge, monolingual LLMs have been developed for under-resourced languages; however, their effectiveness remains less studied when compared to multilingual counterparts on language-specific tasks. In this study, we address this research gap in Greek QA by contributing: (i) DemosQA, a novel dataset, which is constructed using social media user questions and community-reviewed answers to better capture the Greek social and cultural zeitgeist; (ii) a memory-efficient LLM evaluation framework adaptable to diverse QA datasets and languages; and (iii) an extensive evaluation of 11 monolingual and multilingual LLMs on 6 human-curated Greek QA datasets using 3 different prompting strategies. We release our code and data to facilitate reproducibility.