Matching Game Preferences Through Dialogical Large Language Models
A Perspective
- Auteurs : Bellot, Patrice, Egret, Daniel, Fabre, Renaud
-
Description : This perspective paper explores the future potential of “conversational intelligence” by examining how Large Language Models (LLMs) could be combined with GRAPHYP’s network system to better understand human conversations and preferences. Using recent research and case studies, we propose a conceptual framework that could make AI reasoning transparent and traceable, allowing humans to see and understand how AI reaches
its conclusions. We present the conceptual perspective of “Matching Game Preferences through Dialogical Large Language Models (D-LLMs),” a proposed system that would allow multiple users to share their different preferences through structured conversations. This approach envisions personalizing LLMs by embedding individual user preferences directly into how the model makes decisions. The proposed D-LLM framework would require three main components: reasoning processes that could analyze different search experiences and guide performance, classification systems that would identify user preference patterns, and dialogue approaches that could help humans resolve conflicting information. This perspective framework aims to create an interpretable AI system where users could examine, understand, and combine the different human preferences that influence AI responses, detected through GRAPHYP’s search experience networks. The goal of this perspective is to envision AI systems that would not only provide
answers but also show users how those answers were reached, making artificial intelligence more transparent and trustworthy for human decision-making. - Collection : Articles
- Thèmes : Monde de l'Information , Science de l'information
- Licence de diffusion : Licence Creative Commons
- Format : Fichier Adobe PDF
- Date de création : 25 juillet 2025
- Étendue : 29 p.
- Étendue : 487,1 Ko
- Date de publication : 25 juillet 2025
- Langue : en
- Éditeur ou organisme : MDPI
- Sujet(s) : données et contenus numériques , grand modèle de langage (LLM) , intelligence artificielle
- Type de ressource : text