Cultural Alignment

Follow this topic Ask about this topic

Cultural alignment asks whether AI systems respond in ways that fit the values, social norms, languages, and contexts of the communities they serve. Researchers evaluate this with World Values Survey data, localized dilemma and language benchmarks, open-ended generations, and judgments from community members. Approaches include culturally grounded training data and fine-tuning, task-aware adapters and prompts, and inference-time steering or reward models. A central challenge is balancing responsiveness to local norms with within-community diversity: models can match majority views while flattening disagreement, and cultural cues or values may be entangled across languages and contexts.

Latest papers

46 papers4 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

ABench: Adversarily Benchmarking Large Language Models across Taxonomized Values
Oct 20, 2026Liping Yang, Yongqi Leng, Jingting Zheng +3LLM Safety Benchmarks Language Model Safety Evaluation
TJUNLP Lab, School of Computer Science and Technology, Tianjin University, Tianjin, China · Yuanhui AI
Aligning Cultural Behaviors in Arabic Language Models via Preferences
Oct 18, 2026Junhong Liang, Daniil Orel, Saeed Almheiri +11Arabic Language Models Cultural Alignment
Mohamed bin Zayed University of Artificial Intelligence · IBM Research AI
Measuring Cultural Alignment Beyond the Average: A Framework for Evaluating Maternal-Health LLM Interactions in Indian Contexts
Oct 8, 2026Umaira Izhar, Gunjan Arora, Pushpendra SinghCultural Alignment Clinical Language Model Evaluation
Indraprastha Institute of Information Technology Delhi
CRISP: Cultural Reward Modeling for Implicit Situated Propriety
Sep 28, 2026Zekun Yuan, Yangfan Ye, Baohang Li +6Reward Modeling RL for Language Models
Harbin Institute of Technology · Huawei Technologies Co., Ltd · Peng Cheng Laboratory
Supporting and Performing Culture from the Inside
Sep 26, 2026Lea Frermann, Steven BirdCultural Alignment Human-Centered AI
The University of Tübingen, Tübingen, Germany · The University of Melbourne, Melbourne, Australia · Charles Darwin University, Darwin, Australia
Same Values, Different Languages? From Multilingual Probing to Steering LLMs Toward Chinese Social Values
Sep 8, 2026Yuemei Xu, Kexin Xu, Jian Zhou +3Multilingual Language Model Evaluation Cultural Alignment
School of Information Science and Technology, Beijing Foreign Studies University · Beijing Academy of Artificial Intelligence · The State Key Lab of Software Development Environment, Beihang University
Accurate in space, unreliable in time: how LLMs represent national cultural change
Sep 1, 2026Yalda Daryani, Miranda Bogen, Madeleine I. G. DaeppLLM Evaluation Cultural Evolution
Department of Psychology, University of Southern California · Center for Democracy and Technology
Aligned but Flattened: Analyzing the Trade-off between Cultural Alignment and Diversity in LLMs
Sep 1, 2026Jingshen Zhang, Shaoyang Xu, Wenxuan ZhangLLM Evaluation Cultural Alignment
School of Computer Science and Technology, Tianjin University · 2iNLP Lab, Singapore University of Technology and Design
Pak3H: Evaluating the Cost of Cultural Mismatch in LLM Alignment with a Human-Contextualized Urdu Benchmark
Aug 30, 2026Abdullah Hashmat, Usman Naseem, Agha Ali RazaMultilingual Language Model Evaluation LLM Alignment
School of Computing, Macquarie University, Sydney, Australia · Lahore University of Management Sciences, Lahore, Pakistan
CoCoA: Context-Conditional Cultural Alignment for Large Language Models
Aug 30, 2026Kyungdon Lee, Wei Xu, Alan Ritter +2Cultural Bias in Language Models Language Model Debiasing
Sungkyunkwan University, Suwon, South Korea · Georgia Institute of Technology, GA, USA · University of Southern California, CA, USA
Toward Cultural Alignment: Human-Centered Evaluation of Multimodal AI Stories Across Five African Communities
Aug 29, 2026Millicent Ochieng, Felermino D. M. A. Ali, Elizabeth A. Ankrah +8Cultural Alignment Generative AI Evaluation
Microsoft Research Africa · Swansea University · Cornell University +1
Generative AI Alignment with Hinduism's Theological Plurality and Sacred Representation
Aug 28, 2026Dipto Das, Arpita Kundu, Nusrat Jahan Mim +2Human-AI Interaction Cultural Alignment
Department of Computer Science, University of Toronto · Khulna University of Engineering & Technology · Faculty of Architecture, Landscape and Design, University of Toronto +1
PragAlign: Evidence-Sensitive Reply Assistance Across Chinese and Japanese Appropriateness Judgments
Aug 27, 2026Xin Zhong, Satori HachisukaPragmatic Reasoning in Language Models Cultural Alignment
The University of Tokyo
Measuring Cross-Cultural Style Diffusion Through Era Classification: US and Korean Popular Music
Aug 11, 2026Dasol Lee, Minhee Lee, Seonguk Ju +3Cultural Alignment
Music & Arts Learning (MALer) Lab, Sogang University, South Korea · University of Cambridge
LKValues: Aligning Large Language Models with Sri Lankan Societal Values
Jul 22, 2026Nethmi Muthugala, Supryadi, Surangika Ranathunga +7Multilingual Language Model Evaluation LLM Alignment
TJUNLP Lab, School of Computer Science and Technology, Tianjin University, Tianjin, China · School of Mathematical and Computational Sciences, Massey University, Auckland, New Zealand · Department of Computer Science & Engineering, University of Moratuwa, Sri Lanka +2
Pancasila-Dilemmas: Evaluating Large Language Models on Indonesian Human Value Dilemmas Grounded in Pancasila
Jul 20, 2026Supryadi, Irfan, Julianti +4LLM Evaluation LLM Alignment
TJUNLP Lab, School of Computer Science and Technology, Tianjin University, China · Universitas Universal, Indonesia · Beijing Language and Culture University, Beijing, China +2
PLURAL: A Global Dataset for Value Alignment
Jul 9, 2026Dhruv Agarwal, Anya Shukla, Tanya Goyal +1LLM Alignment Cultural Alignment
Cornell University
Plurification in/of language technology -- The integration of culture in next-generation AI
Jun 20, 2026Gertraud Koch, Fausto GiunchigliaCultural Alignment Cultural Bias in Language Models
University of Hamburg, Edmund-Siemers-Allee 1 West, Germany · University of Trento, Dipartimento Ingegneria e Scienza dell'Informazione
The Culture Funnel: You Can't Align What isn't in the Data
Jun 11, 2026Ananya Sahu, Mehrnaz Mofakhami, Daniel D'Souza +3Cultural Alignment Cultural Bias in Language Models
CohereCorrespondingLabs
Scenario-based Probing and Steering Cultural Values in Large Language Models--Extended Version
Jun 9, 2026Trung Duc Anh Dang, Tung Kieu, Sarah MasudLanguage Model Steering Cultural Alignment
University of Copenhagen · Aalborg University
Culturally-Aware AI for Cross-Boundary Community Learning: Undergraduate Innovation at the Intersection of Computation and Design
Jun 8, 2026Jiaojiao Zhao, Weisheng Zhang, Jiawen Cai +2Educational Technology AI in Education
Duke Kunshan University, Suzhou, China · Zhouzhuang Mystery of Life Museum, Suzhou, China · Digital Innovation Research Center and Social Science Division, Duke Kunshan University. Address: Duke Avenue No.8, Kunshan, Suzhou, Jiangsu, China, 215316.
Whose Norms? Disentangling Cultural and Personal Alignment in Large Language Models
Jun 5, 2026Angana Borah, Isabelle Augenstein, Rada MihalceaLLM Alignment Normative Conformity in Language Models
University of Michigan - Ann Arbor · University of Copenhagen
Memetic Capture: A Pluralistic Policy Framework for Governing AI-Driven Cultural Disempowerment
Jun 5, 2026Subramanyam SahooCultural Alignment AI Governance
Horizon Research, City, Country.
Korean Culture into LLM Alignment: Toward Cultural Coherence
Jun 5, 2026MinJae Jung, Minwoo KimLLM Fine-Tuning LLM Safety Alignment
DATUMO Inc.
SEA-NLI: Natural Language Inference as a Lens into Southeast Asian Cultural Understanding
Jun 2, 2026Peerawat Chomphooyod, Jian Gang Ngui, Yosephine Susanto +5Multilingual Language Model Evaluation Cross-Cultural Language Model Evaluation
1Chulalongkorn University · 2AI Singapore · 3MBZUAI +1
Toward Responsible and Epistemically Grounded Multilingual LLMs for Computational Social Science and Humanities
May 30, 2026Wajdi ZaghouaniMultilingual Language Model Evaluation Political Discourse Analysis
Northwestern University in Qatar
Quantifying the Salience of Geo-Cultural Values for Pluralistic Safety Alignment
May 29, 2026Arkadiy Saakyan, Charvi Rastogi, Lora AroyoLanguage Model Safety Evaluation Cultural Alignment
Columbia University, New York, NY, USA. · Google DeepMind, New York, NY, USA.
Cultural Fidelity in English-to-Hindi Translation: A Preservation-Fluency Frontier for Gender Recoverability
May 26, 2026Samyak Savi, Chavi Gupta, Shreyas Gantayet +2Cultural Alignment Machine Translation
BITS Pilani
Cultural Value Alignment Via Latent Activation Steering in Large Language Models
May 25, 2026Trung Duc Anh Dang, Sarah MasudCultural Alignment Cultural Bias in Language Models
University of Copenhagen
Beyond Literal Translation: Evaluating Cultural Effectiveness in Social Media UGC
May 25, 2026Linjuan Wu, Ruiqi Zhang, Xinze Lyu +7Cultural Alignment Machine Translation
Zhejiang University · Xiaohongshu Inc. · Fudan University.

Oct 20, 2026J/K move · Enter open · S save

ABench: Adversarily Benchmarking Large Language Models across Taxonomized Values

Liping Yang, Yongqi Leng, Jingting Zheng, Yuqi Ren+2

TJUNLP Lab, School of Computer Science and Technology, Tianjin University, Tianjin, China · Yuanhui AI

LLM Safety Benchmarks Language Model Safety Evaluation Cultural Alignment Adversarial Robustness of Language Models Cross-Cultural Language Model Evaluation

Open paper AskPDF arXiv

Ensuring the alignment of Large Language Models (LLMs) with diverse cultural values is critical for their safe global deployment. However, existing alignment benchmarks are predominantly English-centric or confined to simple discriminative tasks. Moreover, they often fail to effectively evaluate model robustness against complex, adversarial inductions within specific cultural contexts. To address these limitations, we propose ABench, a fine-grained, handcrafted benchmark specifically tailored to taxonomized values in Chinese. Grounded in a rigorous hierarchical taxonomy comprising 158 derived value subcategories, ABench consists of 2,895 open-ended questions. These questions employ techniques such as role-playing and logical traps to probe the stability of models' stances in adversarially induced contexts. Furthermore, we propose a weighted automated evaluation framework that utilizes question-specific scoring criteria for nuanced assessment. Extensive experiments on 16 mainstream LLMs reveal that most models exhibit significant vulnerabilities when subjected to sophisticated adversary attacks on values (scoring below 60). This underscores the need for more robust, culturally specific alignment strategies. Our data will be publicly released to promote further research on taxonomized value alignment.