Reimagining service delivery in the agentic era with Google Public Sector
cloud.google.com·1d ago
AI Research
arXiv CS.AI·Jun 9·5 min read
Does Persona Make LLMs K-pop Fans? A Pilot Study of LLM-Based Online Concert Audience Agents
TL;DR
Concerts are typically experienced alone through recorded videos, lacking the communal atmosphere. A multi-agent system was developed using persona-based large language models (LLMs) to simulate real-time fan chat during K-pop performances.
✦ Why It Matters
Engineers can leverage persona-based LLMs to enhance user engagement in virtual environments and events.
Key Takeaways
- Explore persona conditioning to improve chat interactions in online events.
- Assess user engagement metrics beyond chat quality for deeper insights.
- Investigate the role of fandom identity in online participation.
- Consider the limitations of LLMs in creating meaningful social experiences.
How It Works
The study utilized a multi-agent system where each LLM agent was conditioned with a specific persona, allowing them to generate chat messages that reflected distinct fan identities. This approach aimed to simulate a more authentic concert atmosphere by mimicking the diverse reactions of a live audience.