"I Recall the Past": Exploring How People Collaborate with Generative AI to Create Cultural Heritage Narratives

2024-12-31

AI Summary

This study investigates how generative AI (GenAI) can effectively support local communities in co-constructing cultural heritage narratives, addressing critical challenges in image generation—including cultural feature distortion, loss of contextual detail, and implicit bias. Employing Stable Diffusion–based image synthesis, human-AI collaborative workshops, and qualitative narrative analysis, the research identifies three culturally grounded narrative strategies: “illuminating,” “amplifying,” and “reinterpreting.” A novel Cultural Feature Bias Assessment Framework is developed and empirically applied, revealing that while GenAI enhances narrative agency, it suffers from weak cultural accuracy, low controllability, and insufficient bias mitigation. The study innovatively proposes three synergistic intervention pathways: prompt engineering optimization, lightweight model fine-tuning, and construction of culturally sensitive training datasets. These contributions advance both theoretical understanding and practical methodologies for fostering trustworthy, equitable human-AI collaboration in cultural heritage contexts.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Philosophy and Ethics of AI: Bias, Fairness & Equity
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Visitors to cultural heritage sites often encounter official information, while local people's unofficial stories remain invisible. To explore expression of local narratives, we conducted a workshop with 20 participants utilizing Generative AI (GenAI) to support visual narratives, asking them to use Stable Diffusion to create images of familiar cultural heritage sites, as well as images of unfamiliar ones for comparison. The results revealed three narrative strategies and highlighted GenAI's strengths in illuminating, amplifying, and reinterpreting personal narratives. However, GenAI showed limitations in meeting detailed requirements, portraying cultural features, and avoiding bias, which were particularly pronounced with unfamiliar sites due to participants' lack of local knowledge. To address these challenges, we recommend providing detailed explanations, prompt engineering, and fine-tuning AI models to reduce uncertainties, using objective references to mitigate inaccuracies from participants' inability to recognize errors or misconceptions, and curating datasets to train AI models capable of accurately portraying cultural features.

Problem

• Generative AI
• Cultural Heritage Representation
• Bias and Accuracy in AI

Innovation

• Generative AI
• Cultural Heritage Visualization
• Enhanced Detail Recognition