SearcharxivSearch

arXiv subjects

Julian Alvarez

Publications and source records attributed to Julian Alvarez.

2 recordsLinked to original sources

Perspective: The creation of "Newsgames" as a teaching method-Empirical observations

This chapter reports an empirical teaching experience integrating newsgame creation-serious games addressing current events and contributing to public debate-into an introductory game design course for engineering students. From 2010 to 2012, around 80 students produced 17 games on diverse news topics (e.g., H1N1 influenza, Megaupload shutdown, Tunisian Revolution, Haiti earthquake), relying on online journalistic sources and using accessible development tools suited to mixed programming backgrounds (RPG Maker, The Games Factory 2, Flash, Java). The authors argue that designing newsgames fosters learning outcomes beyond technical design skills: (1) thorough information seeking and documentation of real-world issues, (2) exchange and confrontation of viewpoints through contrasting game interpretations of the same event, and (3) classroom debates about the legitimacy and limits of video games as an expressive medium for sensitive topics. The paper concludes that newsgame design can support the development of reasoning skills (evidence-based argumentation and perspective-taking) and suggests extending the approach to other serious game types to further explore its educational potential.

cs.CY

Role-Playing Evaluation for Large Language Models

Large Language Models (LLMs) demonstrate a notable capacity for adopting personas and engaging in role-playing. However, evaluating this ability presents significant challenges, as human assessments are resource-intensive and automated evaluations can be biased. To address this, we introduce Role-Playing Eval (RPEval), a novel benchmark designed to assess LLM role-playing capabilities across four key dimensions: emotional understanding, decision-making, moral alignment, and in-character consistency. This article details the construction of RPEval and presents baseline evaluations. Our code and dataset are available at https://github.com/yelboudouri/RPEval

cs.CL