Pragmatics Meets Culture: Culturally-adapted Artwork Description Generation and Evaluation
This addresses cultural bias in AI language models for art description, benefiting diverse audiences, but it is incremental as it builds on existing pragmatic models.
The paper tackles the problem of cultural bias in open-ended text generation by introducing culturally-adapted art description generation, where models describe artworks for audiences with varying cultural familiarity, and finds that a pragmatic speaker model improves simulated listener comprehension by up to 8.2% and is rated as more helpful by 8.0% in a human study.
Language models are known to exhibit various forms of cultural bias in decision-making tasks, yet much less is known about their degree of cultural familiarity in open-ended text generation tasks. In this paper, we introduce the task of culturally-adapted art description generation, where models describe artworks for audiences from different cultural groups who vary in their familiarity with the cultural symbols and narratives embedded in the artwork. To evaluate cultural competence in this pragmatic generation task, we propose a framework based on culturally grounded question answering. We find that base models are only marginally adequate for this task, but, through a pragmatic speaker model, we can improve simulated listener comprehension by up to 8.2%. A human study further confirms that the model with higher pragmatic competence is rated as more helpful for comprehension by 8.0%.