Salvato in:
Dettagli Bibliografici
Autori principali: Au, Steven, Lin, Baihan
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.07788
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908949191589888
author Au, Steven
Lin, Baihan
author_facet Au, Steven
Lin, Baihan
contents We introduce PeReGrINE, a benchmark and evaluation framework for personalized review generation grounded in graph-structured user--item evidence. PeReGrINE restructures Amazon Reviews 2023 into a temporally consistent bipartite graph, where each target review is conditioned on bounded evidence from user history, item context, and neighborhood interactions under explicit temporal cutoffs. To represent persistent user preferences without conditioning directly on sparse raw histories, we compute a User Style Parameter that summarizes each user's linguistic and affective tendencies over prior reviews. This setup supports controlled comparison of four graph-derived retrieval settings: product-only, user-only, neighbor-only, and combined evidence. Beyond standard generation metrics, we introduce Dissonance Analysis, a macro-level evaluation framework that measures deviation from expected user style and product-level consensus. We also study visual evidence as an auxiliary context source and find that it can improve textual quality in some settings, while graph-derived evidence remains the main driver of personalization and consistency. Across product categories, PeReGrINE offers a reproducible way to study how evidence composition affects review fidelity, personalization, and grounding in retrieval-conditioned language models.
format Preprint
id arxiv_https___arxiv_org_abs_2604_07788
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PeReGrINE: Evaluating Personalized Review Fidelity with User Item Graph Context
Au, Steven
Lin, Baihan
Information Retrieval
Computation and Language
We introduce PeReGrINE, a benchmark and evaluation framework for personalized review generation grounded in graph-structured user--item evidence. PeReGrINE restructures Amazon Reviews 2023 into a temporally consistent bipartite graph, where each target review is conditioned on bounded evidence from user history, item context, and neighborhood interactions under explicit temporal cutoffs. To represent persistent user preferences without conditioning directly on sparse raw histories, we compute a User Style Parameter that summarizes each user's linguistic and affective tendencies over prior reviews. This setup supports controlled comparison of four graph-derived retrieval settings: product-only, user-only, neighbor-only, and combined evidence. Beyond standard generation metrics, we introduce Dissonance Analysis, a macro-level evaluation framework that measures deviation from expected user style and product-level consensus. We also study visual evidence as an auxiliary context source and find that it can improve textual quality in some settings, while graph-derived evidence remains the main driver of personalization and consistency. Across product categories, PeReGrINE offers a reproducible way to study how evidence composition affects review fidelity, personalization, and grounding in retrieval-conditioned language models.
title PeReGrINE: Evaluating Personalized Review Fidelity with User Item Graph Context
topic Information Retrieval
Computation and Language
url https://arxiv.org/abs/2604.07788