Against 'softmaxing' culture

TL;DR

This paper critiques the homogenization of culture by large AI models, called 'softmaxing culture,' and advocates for new evaluation approaches that focus on the contextual and relational aspects of culture rather than static definitions.

Contribution

It introduces two conceptual shifts in cultural evaluation: questioning 'when is culture?' instead of 'what is culture?', and emphasizing the relation of universals to particulars.

Findings

Current evaluations homogenize cultural expressions.

Proposes shifting focus to cultural contexts and relations.

Highlights limitations of ML and HCI approaches.

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.