Beyond Value Elicitation: Towards Moral Profiles in Early Requirements Engineering via Role-Playing Games and Anthropologist LLMs

Abstract This study presents a proof of concept of an approach to eliciting and representing the individual moral profile of digital systems users in Requirements Engineering (RE) by combining immersive role-playing games (RPGs) with large language model (LLM) analysis. While existing approaches rely on predefined value taxonomies and explicit articulation, values are frequently tacit, context-dependent, and difficult to express directly. To address these limitations, we propose a shift from eliciting discrete moral values to reconstructing and representing users’ moral profiles in narrative form. Grounded in phenomenological and narrative anthropology, the proposed approach focuses on capturing users’ moral orientations as it emerges through situated decision-making. RPG sessions are used to generate context-rich narrative data, which are then analyzed by a specialized LLM (GPT-A) to produce individual anthropological moral profiles (IAMP). A validation process based on a cross-comparison between model outputs and participants’ responses in unseen moral scenarios is used to assess the adequacy of the generated representations. Results indicate that RPG environments effectively support the generation of rich, context-dependent data for eliciting tacit values, that an anthropologically grounded LLM can transform such data into coherent narrative representations of users’ moral profiles, and that these representations enable the contextual interpretation of users’ preferences and values within the given domain, with improved performance when interpretive framing captures relationships between actions, underlying motivations, and individual domain expertise. From an RE perspective, this enables the analysis of user preferences and trade-offs in a way that preserves their situated and dynamic nature, providing a foundation for integrating human moral values into early-stage of requirements engineering.