Traditional recommender systems lack transparency, limiting user trust. This paper presents ARgumentationbased Explainable recommender System-ARES, which offers traceable recommendations with explicit reasoning paths. For explainability ARES relies upon ABALearn, a system that learns Assumption-Based Argumentation (ABA) frameworks from positive and negative examples, given a background knowledge. Argumentative explanations are reformulated into natural language via a Large Language Model, linked in ABA logic to prevent hallucinations. The system uses an iterative learning mechanism, guided by ABALearn, and facilitated by an interactive chatbot, to dynamically adapt user profiles.
Felici, R., De Angelis, E., Ferrato, A., Proietti, M., Sansonetti, G., Toni, F. (2025). Argumentation-based explainable recommender system with ARES. In CEUR Workshop Proceedings (pp.8-19). Aachen : CEUR-WS.
Argumentation-based explainable recommender system with ARES
Ferrato A.;Sansonetti G.;
2025-01-01
Abstract
Traditional recommender systems lack transparency, limiting user trust. This paper presents ARgumentationbased Explainable recommender System-ARES, which offers traceable recommendations with explicit reasoning paths. For explainability ARES relies upon ABALearn, a system that learns Assumption-Based Argumentation (ABA) frameworks from positive and negative examples, given a background knowledge. Argumentative explanations are reformulated into natural language via a Large Language Model, linked in ABA logic to prevent hallucinations. The system uses an iterative learning mechanism, guided by ABALearn, and facilitated by an interactive chatbot, to dynamically adapt user profiles.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
