LLMs and RPGs help engineers understand user moral profiles

Researchers have developed a novel method for understanding users' moral values in early software development by using role-playing games and large language models. This approach moves beyond traditional value elicitation by having participants engage in simulated scenarios, generating rich narrative data. A specialized LLM, termed GPT-A, then analyzes this data to create individual anthropological moral profiles (IAMPs), which represent users' moral orientations in context. AI

IMPACT Introduces a novel method for integrating user moral values into system design, potentially improving user-centric AI development.

RANK_REASON This is a research paper published on arXiv detailing a new methodology for requirements engineering. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• Requirements Engineering
• GPT-A

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →