Toward Holistic Evaluation of Recommender Systems Powered by Generative Models

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Deldjoo, Yashar, Mehta, Nikhil, Sathiamoorthy, Maheswaran, Zhang, Shuai, Castells, Pablo, McAuley, Julian
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918088110243840
author Deldjoo, Yashar
Mehta, Nikhil
Sathiamoorthy, Maheswaran
Zhang, Shuai
Castells, Pablo
McAuley, Julian
author_facet Deldjoo, Yashar
Mehta, Nikhil
Sathiamoorthy, Maheswaran
Zhang, Shuai
Castells, Pablo
McAuley, Julian
contents Recommender systems powered by generative models (Gen-RecSys) extend beyond classical item ranking by producing open-ended content, which simultaneously unlocks richer user experiences and introduces new risks. On one hand, these systems can enhance personalization and appeal through dynamic explanations and multi-turn dialogues. On the other hand, they might venture into unknown territory-hallucinating nonexistent items, amplifying bias, or leaking private information. Traditional accuracy metrics cannot fully capture these challenges, as they fail to measure factual correctness, content safety, or alignment with user intent. This paper makes two main contributions. First, we categorize the evaluation challenges of Gen-RecSys into two groups: (i) existing concerns that are exacerbated by generative outputs (e.g., bias, privacy) and (ii) entirely new risks (e.g., item hallucinations, contradictory explanations). Second, we propose a holistic evaluation approach that includes scenario-based assessments and multi-metric checks-incorporating relevance, factual grounding, bias detection, and policy compliance. Our goal is to provide a guiding framework so researchers and practitioners can thoroughly assess Gen-RecSys, ensuring effective personalization and responsible deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2504_06667
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Toward Holistic Evaluation of Recommender Systems Powered by Generative Models
Deldjoo, Yashar
Mehta, Nikhil
Sathiamoorthy, Maheswaran
Zhang, Shuai
Castells, Pablo
McAuley, Julian
Information Retrieval
Artificial Intelligence
Recommender systems powered by generative models (Gen-RecSys) extend beyond classical item ranking by producing open-ended content, which simultaneously unlocks richer user experiences and introduces new risks. On one hand, these systems can enhance personalization and appeal through dynamic explanations and multi-turn dialogues. On the other hand, they might venture into unknown territory-hallucinating nonexistent items, amplifying bias, or leaking private information. Traditional accuracy metrics cannot fully capture these challenges, as they fail to measure factual correctness, content safety, or alignment with user intent. This paper makes two main contributions. First, we categorize the evaluation challenges of Gen-RecSys into two groups: (i) existing concerns that are exacerbated by generative outputs (e.g., bias, privacy) and (ii) entirely new risks (e.g., item hallucinations, contradictory explanations). Second, we propose a holistic evaluation approach that includes scenario-based assessments and multi-metric checks-incorporating relevance, factual grounding, bias detection, and policy compliance. Our goal is to provide a guiding framework so researchers and practitioners can thoroughly assess Gen-RecSys, ensuring effective personalization and responsible deployment.
title Toward Holistic Evaluation of Recommender Systems Powered by Generative Models
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2504.06667