Work

Leveraging LLMs to Explain the Consequences of Recommendations

Year: 2025

Type: conference-paper

Abstract: Recommender systems help users make better decisions by suggesting products that match their preferences.However, users often do not understand why certain products are recommended, which can reduce trust and satisfaction.While explanations address this issue, they often fail to communicate the individual impact the decision for an item will have.To address this, we present an LLM-based framework for generating consequence-based explanations.These explanations provide comprehensible personalized insights into the positive and negative consequences of user decisions.To support the assessment and selection of the most effective prompting strategy, we introduce evaluation metrics tailored to consequenceaware explanations and systematically compare different prompting strategies for an apartment recommendation example.

Source: ACM Conference on User Modeling, Adaptation and Personalization (UMAP)

DOI: 10.1145/3699682.3728328

Authors: Sebastian Lubos, Michael Gartner, Alexander Felfernig, Reinhard Willfort

Institution: Graz University of Technology

Language: English

Topic: Explainable Artificial Intelligence (XAI)

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: Österreichische Forschungsförderungsgesellschaft

Award: G7262146358