Educational game for conflict mediation training in wartime conditions using large language models DOI Creative Commons

Sophia V. Ilkova,

Pavlo V. Merzlykin, Наталя Володимирівна Моісеєнко

и другие.

CTE Workshop Proceedings, Год журнала: 2025, Номер unknown

Опубликована: Март 18, 2025

Interpersonal conflicts increase significantly during wartime, negatively impacting psychological well-being and social cohesion. This research introduces an innovative educational game that teaches mediation skills through interactive dialogue with characters generated by large language models (LLMs). The features dynamically personalized responses based on player actions, allowing users to practice strategies in a safe, repeatable environment. We implemented the system using Gemini 1.5 Flash LLM conducted experiments optimize model parameters evaluate effectiveness of different strategies. Our results demonstrate compensation strategy proves most effective our conflict scenarios. provides quantitative method for evaluating strategies, which has been impossible real-world settings. novel approach fills significant gap education, offering accessible tool training mediators, particularly conflict-affected regions such as Ukraine.

Язык: Английский

Educational game for conflict mediation training in wartime conditions using large language models DOI Creative Commons

Sophia V. Ilkova,

Pavlo V. Merzlykin, Наталя Володимирівна Моісеєнко

и другие.

CTE Workshop Proceedings, Год журнала: 2025, Номер unknown

Опубликована: Март 18, 2025

Interpersonal conflicts increase significantly during wartime, negatively impacting psychological well-being and social cohesion. This research introduces an innovative educational game that teaches mediation skills through interactive dialogue with characters generated by large language models (LLMs). The features dynamically personalized responses based on player actions, allowing users to practice strategies in a safe, repeatable environment. We implemented the system using Gemini 1.5 Flash LLM conducted experiments optimize model parameters evaluate effectiveness of different strategies. Our results demonstrate compensation strategy proves most effective our conflict scenarios. provides quantitative method for evaluating strategies, which has been impossible real-world settings. novel approach fills significant gap education, offering accessible tool training mediators, particularly conflict-affected regions such as Ukraine.

Язык: Английский

Процитировано

0