Reimagining service delivery in the agentic era with Google Public Sector
cloud.google.com·1d ago
AI Research
arXiv CS.AI·Jun 12·5 min read
Divination by Prompt: LLM-Mediated Xuanxue on Chinese Social Media
TL;DR
A gap existed in understanding how large language models (LLMs) are used for divination on Chinese social media. Researchers conducted a mixed-methods study analyzing over 23,000 posts and 32 interviews to explore user interactions with LLMs in the context of Xuanxue, a term for mystical practices.
✦ Why It Matters
Engineers and researchers can explore user interaction patterns with AI to enhance AI-driven applications in cultural contexts.
Key Takeaways
- Explore user engagement with LLMs for personal guidance.
- Recognize the role of cognitive biases in interpreting AI outputs.
- Investigate the collaborative nature of prompt engineering.
- Understand the tension between traditional and modern divination practices.
How It Works
Users interact with LLMs by refining prompts collaboratively, which allows them to tailor the AI's responses to their specific concerns. This active engagement transforms users into co-creators of the divination process, enhancing their connection to the outcomes.