Using a Large Language Model as Design Material for an Interactive Museum Installation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909556045512704 |
|---|---|
| author | Engstrøm, Maria Padilla Løvlie, Anders Sundnes |
| author_facet | Engstrøm, Maria Padilla Løvlie, Anders Sundnes |
| contents | We present a work in progress that explores using a Large Language Model (LLM) as a design material for an interactive museum installation. LLMs offer the possibility of creating chatbots that can facilitate dynamic and human-like conversation, engaging in a form of role play to bring historical persons to life for visitors. However, LLMs are prone to producing misinformation, which runs counter to museums' core mission to educate the public. We use Research-through-Design to explore some approaches to navigating this dilemma through rapid prototyping and evaluation and propose some directions for further research. We suggest that designers may shape interactions with the chatbot to emphasize personal narratives and role play rather than historical facts or to intentionally highlight the unreliability of the chatbot outputs to provoke critical reflection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_22345 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Using a Large Language Model as Design Material for an Interactive Museum Installation Engstrøm, Maria Padilla Løvlie, Anders Sundnes Human-Computer Interaction We present a work in progress that explores using a Large Language Model (LLM) as a design material for an interactive museum installation. LLMs offer the possibility of creating chatbots that can facilitate dynamic and human-like conversation, engaging in a form of role play to bring historical persons to life for visitors. However, LLMs are prone to producing misinformation, which runs counter to museums' core mission to educate the public. We use Research-through-Design to explore some approaches to navigating this dilemma through rapid prototyping and evaluation and propose some directions for further research. We suggest that designers may shape interactions with the chatbot to emphasize personal narratives and role play rather than historical facts or to intentionally highlight the unreliability of the chatbot outputs to provoke critical reflection. |
| title | Using a Large Language Model as Design Material for an Interactive Museum Installation |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2503.22345 |