A carregar...
Publicação
Prompt-gaming: a pilot study on LLM-evaluating agent in a meaningful energy game
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 3.39 MB | Adobe PDF |
Orientador(es)
Resumo(s)
Building on previous work on incorporating large language mod
els (LLM) in gaming, we investigate the possibility of implement
ing LLM as evaluating agents of open-ended challenges in serious
games and its potential to facilitate a meaningful experience for
the player. We contribute with a sustainability game prototype in
a single natural language prompt about energy communities and
we tested it with 13 participants inside ChatGPT-3.5. Two partici
pants were already aware of energy communities before the game,
and eight of the remaining 11 gained valuable knowledge about
the specifc topic. Comparing ChatGPT-3.5 evaluations of players’
interaction with an expert’s assessment, ChatGPT-3.5 correctly
evaluated 81% of player’s answers. Our results are encouraging
and show the potential of using LLMs as mediating agents in ed
ucational games, while also allowing easy prototyping of games
through natural language prompts.
Descrição
Palavras-chave
Large Language Models (LLMs) Serious games Game-based Learning Sustainability Energy communities Natural Language Pro cessing (NLP) . Faculdade de Ciências Exatas e da Engenharia
Contexto Educativo
Citação
Andrés Isaza-Giraldo, Paulo Bala, Pedro F. Campos, and Lucas Pereira. 2024. Prompt-Gaming: A Pilot Study on LLM-Evaluating Agent in a Meaningful Energy Game. In Extended Abstracts of the CHI Conference on Human Factorsin Computing Systems (CHI EA ’24), May 11–16, 2024
Editora
Association for Computing Machinery (ACM)