Against 'softmaxing' culture

• URL: http://arxiv.org/abs/2506.22968v2
• Date: Tue, 01 Jul 2025 10:45:21 GMT
• Title: Against 'softmaxing' culture
• Authors: Daniel Mwesigwa,
• Abstract summary: I call this phenomenon "softmaxing culture," and it is one of the fundamental challenges facing AI evaluations today.<n>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?"<n>I acknowledge the philosophical claim that cultural universals exist, but the challenge is not simply to describe them, but to situate them in relation to their particulars.
• Score: 0.21756081703275998
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• From Word to World: Evaluate and Mitigate Culture Bias via Word Association Test [48.623761108859085]
  We extend the human-centered word association test (WAT) to assess the alignment of large language models with cross-cultural cognition.<n>To mitigate the culture preference, we propose CultureSteer, an innovative approach that integrates a culture-aware steering mechanism.
  arXiv  Detail & Related papers  (2025-05-24T07:05:10Z)
• AI as a deliberative partner fosters intercultural empathy for Americans but fails for Latin American participants [4.641694322213005]
  We examined how different types of AI interaction, i.e. deliberative versus non-deliberative and culturally aligned versus non-aligned, affect intercultural empathy.<n>Results show that deliberative conversations increased intercultural empathy among American participants but not Latin American participants.<n>Despite explicit prompting and instruction to represent cultural perspectives in participants' native languages, AI systems still exhibit significant disparities in cultural representation.
  arXiv  Detail & Related papers  (2025-04-04T17:15:01Z)
• Mind the Gesture: Evaluating AI Sensitivity to Culturally Offensive Non-Verbal Gestures [67.89565097372751]
  Gestures are an integral part of non-verbal communication, with meanings that vary across cultures.<n>As AI systems become more integrated into global applications, ensuring they do not inadvertently perpetuate cultural offenses is critical.<n>We introduce Multi-Cultural Set of Inappropriate Gestures and Nonverbal Signs (MC-SIGNS), a dataset of 288 gesture-country pairs annotated for offensiveness, cultural significance, and contextual factors.
  arXiv  Detail & Related papers  (2025-02-24T23:10:08Z)
• Rethinking AI Cultural Alignment [1.8434042562191815]
  We show that humans' cultural values must be understood within the context of specific AI systems.<n>We argue that cultural alignment should be reframed as a bidirectional process.
  arXiv  Detail & Related papers  (2025-01-13T23:42:37Z)
• CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 Countries [63.00147630084146]
  Vision-language models (VLMs) have advanced human-AI interaction but struggle with cultural understanding.<n>CultureVerse is a large-scale multimodal benchmark covering 19, 682 cultural concepts, 188 countries/regions, 15 cultural concepts, and 3 question types.<n>We propose CultureVLM, a series of VLMs fine-tuned on our dataset to achieve significant performance improvement in cultural understanding.
  arXiv  Detail & Related papers  (2025-01-02T14:42:37Z)
• Extrinsic Evaluation of Cultural Competence in Large Language Models [53.626808086522985]
  We focus on extrinsic evaluation of cultural competence in two text generation tasks. We evaluate model outputs when an explicit cue of culture, specifically nationality, is perturbed in the prompts. We find weak correlations between text similarity of outputs for different countries and the cultural values of these countries.
  arXiv  Detail & Related papers  (2024-06-17T14:03:27Z)
• CulturePark: Boosting Cross-cultural Understanding in Large Language Models [63.452948673344395]
  This paper introduces CulturePark, an LLM-powered multi-agent communication framework for cultural data collection. It generates high-quality cross-cultural dialogues encapsulating human beliefs, norms, and customs. We evaluate these models across three downstream tasks: content moderation, cultural alignment, and cultural education.
  arXiv  Detail & Related papers  (2024-05-24T01:49:02Z)
• Cultural Bias and Cultural Alignment of Large Language Models [0.9374652839580183]
  We conduct a disaggregated evaluation of cultural bias for five widely used large language models. All models exhibit cultural values resembling English-speaking and Protestant European countries. We suggest using cultural prompting and ongoing evaluation to reduce cultural bias in the output of generative AI.
  arXiv  Detail & Related papers  (2023-11-23T16:45:56Z)
• Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models [89.94270049334479]
  This paper identifies a cultural dominance issue within large language models (LLMs) LLMs often provide inappropriate English-culture-related answers that are not relevant to the expected culture when users ask in non-English languages.
  arXiv  Detail & Related papers  (2023-10-19T05:38:23Z)
• An Analytics of Culture: Modeling Subjectivity, Scalability, Contextuality, and Temporality [13.638494941763637]
  There is a bidirectional relationship between culture and AI; AI models are increasingly used to analyse culture, thereby shaping our understanding of culture. On the other hand, the models are trained on collections of cultural artifacts thereby implicitly, and not always correctly, encoding expressions of culture. This creates a tension that both limits the use of AI for analysing culture and leads to problems in AI with respect to cultural complex issues such as bias.
  arXiv  Detail & Related papers  (2022-11-14T15:42:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.