ICML 2026 Workshop
Culture × AI
Evaluating AI as a Cultural Technology
About the Workshop
What do we want from AI in the cultural dimension?
Generative AI is increasingly recognised as a social and cultural technology. These systems process an enormous amount of social data to produce novel cultural artefacts, such as text, images, and videos. While much progress has been made in evaluating cultural aspects of AI, it has tended to focus on harm mitigation: identifying and preventing moral violations, the spread of bias and misinformation, and deviation from human values. But a more positive or constructive notion of culture in AI remains underdeveloped. How can we evaluate cultural aspects of AI technology in a way that not only seeks to avoid failure, but gives a more robust definition of success?
This workshop covers current approaches for evaluating cultural aspects of generative AI. Our primary focus is on work that aims to bring ideas and techniques from the humanities, arts, and qualitative social sciences upstream in AI development. We'll bring together a range of work at the intersection of culture and AI, with the goal of not just studying the effects of AI after deployment but also in actively shaping the design of the technology itself. The workshop will give special focus to research that seeks to articulate a "positive" vision for cultural AI.
A key theme in this workshop will be what we call Interpretive Technologies: approaches that take seriously the role of interpretive methods in understanding and improving AI systems. In many ways, the outputs of today's AI models resemble the kind of cultural artefacts traditionally studied by humanists. This means AI is not just a tool that produces culture; it is itself engaged in acts of interpretation. The research brought together for this workshop is designed to take this seriously: research that asks how humanistic traditions of meaning-making, contextual sensitivity, and aesthetic judgment can be embedded in AI design, not just applied after the fact.
Crucially, this workshop will seek to grapple directly with the tensions this research raises. Building AI systems that can "do" culture more effectively is not an unambiguous good: it poses real risks for artists, creative practitioners, and the broader cultural ecosystem. Ultimately, a positive vision for cultural AI will have to reckon with this.
Schedule
Friday 10 July 2026
COEX Conference Room 307
Invited Speakers
Keynote Talks
Accepted Oral Papers
Lightning Talks
"Spoiler Alert: Narrative Forecasting as a Metric for Tension in LLM Storytelling"
"Does Persona Make LLM a K-pop Fan? A Pilot Study of LLM-Based Online Concert Audience Agents"
"Where Models Concentrate and Humans Spread: Toward Cultural Reach in Generative AI"
"Reading Models' Self-Defense: Narratology as Legibility Instrument for Cultural AI Evaluation"
"A Charter for Cultural AI Evaluation: Methodological Principles for Long-Tail, Cross-Cultural Tasks"
Organisers
The Team
Drew Hemment
Co-lead Organiser
Theme Lead, Interpretive Technologies
The Alan Turing Institute
Professor of Data Arts & Society, University of Edinburgh
Canfer Akbulut
Organiser
Senior Research Scientist
Google DeepMind
Meredith Martin
Organiser
Professor, Institute Director for Digital Humanities
Princeton University
Adam Sobey
Organiser
Mission Director for Sustainability
The Alan Turing Institute
Professor in AI and Engineering, University of Southampton
Matt Wilkens
Organiser
Associate Professor, Information Science & Digital Humanities
Cornell University