Recent advances in Large Language Models (LLMs) have expanded their role in human interaction, yet curiosity -- a central driver of inquiry -- remains underexplored in these systems, particularly across cultural contexts. In this work, we investigate cultural variation in curiosity using Yahoo! Answers, a real-world multi-country dataset spanning diverse topics. We introduce CUEST (CUriosity Evaluation across SocieTies), an evaluation framework that measures human-model alignment in curiosity through linguistic (style), topic preference (content) analysis and grounding insights in social science constructs. Across open- and closed-source models, we find that LLMs flatten cross-cultural diversity, aligning more closely with how curiosity is expressed in Western countries. We then explore fine-tuning strategies to induce curiosity in LLMs, narrowing the human-model alignment gap by up to 50%. Finally, we demonstrate the practical value of curiosity for LLM adaptability across cultures, showing its importance for future NLP research.

AI is flattening culture. Evaluations of "culture" are showing the myriad ways in which large AI models are homogenizing language and culture, averaging out rich linguistic differences into generic expressions. I call this phenomenon "softmaxing culture,'' and it is one of the fundamental challenges facing AI evaluations today. Efforts to improve and strengthen evaluations of culture are central to the project of cultural alignment in large AI systems. This position paper argues that machine learning (ML) and human-computer interaction (HCI) approaches to evaluation are limited. I propose two key conceptual shifts. First, instead of asking "what is culture?" at the start of system evaluations, I propose beginning with the question: "when is culture?" Second, while I acknowledge the philosophical claim that cultural universals exist, the challenge is not simply to describe them, but to situate them in relation to their particulars. Taken together, these conceptual shifts invite evaluation approaches that move beyond technical requirements toward perspectives that are more responsive to the complexities of culture.

Large Language Model (LLM) alignment conventionally relies on supervised fine-tuning or reinforcement learning based alignment frameworks. These methods typically require labeled or preference datasets and involve updating model weights to align the LLM with the training objective or reward model. Meanwhile, in social sciences such as cross-cultural studies, factor analysis is widely used to uncover underlying dimensions or latent variables that explain observed patterns in survey data. The non-differentiable nature of these measurements deriving from survey data renders the former alignment methods infeasible for alignment with cultural dimensions. To overcome this, we propose a parameter efficient strategy that combines soft prompt tuning, which freezes the model parameters while modifying the input prompt embeddings, with Differential Evolution (DE), a black-box optimization method for cases where a differentiable objective is unattainable. This strategy ensures alignment consistency without the need for preference data or model parameter updates, significantly enhancing efficiency and mitigating overfitting. Our method demonstrates significant improvements in LLama-3-8B-Instruct's cultural dimensions across multiple regions, outperforming both the Naive LLM and the In-context Learning (ICL) baseline, and effectively bridges computational models with human cultural nuances.

Qatar's football sector has undergone a substantial technological transformation with the implementation of Electronic Performance and Tracking Systems (EPTS). This study examines the impact of cultural and technological factors on EPTS adoption, using Hofstede's Cultural Dimensions Theory and the Technology Acceptance Model (TAM) as theoretical frameworks. An initial exploratory study involved ten participants, followed by an expanded dataset comprising thirty stakeholders, including players, coaches, and staff from Qatari football organizations. Multiple regression analysis was conducted to evaluate the relationships between perceived usefulness, perceived ease of use, power distance, innovation receptiveness, integration complexity, and overall adoption. The results indicate that perceived usefulness, innovation receptiveness, and lower power distance significantly drive EPTS adoption, while ease of use is marginally significant and integration complexity is non-significant in this sample. These findings provide practical insights for sports technology stakeholders in Qatar and emphasize the importance of aligning cultural considerations with technological readiness for successful EPTS integration.

A large number of studies rely on closed-style multiple-choice surveys to evaluate cultural alignment in Large Language Models (LLMs). In this work, we challenge this constrained evaluation paradigm and explore more realistic, unconstrained approaches. Using the World Values Survey (WVS) and Hofstede Cultural Dimensions as case studies, we demonstrate that LLMs exhibit stronger cultural alignment in less constrained settings, where responses are not forced. Additionally, we show that even minor changes, such as reordering survey choices, lead to inconsistent outputs, exposing the limitations of closed-style evaluations. Our findings advocate for more robust and flexible evaluation frameworks that focus on specific cultural proxies, encouraging more nuanced and accurate assessments of cultural alignment in LLMs.

Although LLMs have been extremely effective in a large number of complex tasks, their understanding and functionality for regional languages and cultures are not well studied. In this paper, we explore the ability of various LLMs to comprehend the cultural aspects of two regional languages: Malayalam (state of Kerala, India) and Yoruba (West Africa). Using Hofstede's six cultural dimensions: Power Distance (PDI), Individualism (IDV), Motivation towards Achievement and Success (MAS), Uncertainty Avoidance (UAV), Long Term Orientation (LTO), and Indulgence (IVR), we quantify the cultural awareness of LLM-based responses. We demonstrate that although LLMs show a high cultural similarity for English, they fail to capture the cultural nuances across these 6 metrics for Malayalam and Yoruba. We also highlight the need for large-scale regional language LLM training with culturally enriched datasets. This will have huge implications for enhancing the user experience of chat-based LLMs and also improving the validity of large-scale LLM agent-based market research.

Productive interactions between diverse users and language technologies require outputs from the latter to be culturally relevant and sensitive. Prior works have evaluated models' knowledge of cultural norms, values, and artifacts, without considering how this knowledge manifests in downstream applications. In this work, we focus on extrinsic evaluation of cultural competence in two text generation tasks, open-ended question answering and story generation. We quantitatively and qualitatively evaluate model outputs when an explicit cue of culture, specifically nationality, is perturbed in the prompts. Although we find that model outputs do vary when varying nationalities and feature culturally relevant words, we also find weak correlations between text similarity of outputs for different countries and the cultural values of these countries. Finally, we discuss important considerations in designing comprehensive evaluation of cultural competence in user-facing tasks.

The deployment of large language models (LLMs) raises concerns regarding their cultural misalignment and potential ramifications on individuals from various cultural norms. Existing work investigated political and social biases and public opinions rather than their cultural values. To address this limitation, the proposed Cultural Alignment Test (CAT) quantifies cultural alignment using Hofstede's cultural dimension framework, which offers an explanatory cross-cultural comparison through the latent variable analysis. We apply our approach to assess the cultural values embedded in state-of-the-art LLMs, such as: ChatGPT and Bard, across diverse cultures of countries: United States (US), Saudi Arabia, China, and Slovakia, using different prompting styles and hyperparameter settings. Our results not only quantify cultural alignment of LLMs with certain countries, but also reveal the difference between LLMs in explanatory cultural dimensions. While all LLMs did not provide satisfactory results in understanding cultural values, GPT-4 exhibited the highest CAT score for the cultural values of the US.