PeReGrINE: Evaluating Personalized Review Fidelity with User Item Graph Context
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 16 of its 19 references that are in the map. First posted on arXiv 9 Apr 2026.
Builds on
16 of 19 references.
References · 16
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
- 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,139
- 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 828
- 2019Neural Graph Collaborative Filteringcited by 661
- 2021CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrievalcited by 651
- 2023LaMP: When Large Language Models Meet Personalizationcited by 437
- 2019KGAT: Knowledge Graph Attention Network for Recommendationcited by 343
- 2023PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traitscited by 234
- 2024Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoderscited by 224
- 2019TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agentscited by 188
- 2015VBPR: Visual Bayesian Personalized Ranking from Implicit Feedbackcited by 151
4 more
- 2023Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrieverscited by 92
- 2022Personalized Showcases: Generating Multi-Modal Explanations for Recommendationscited by 30
- 2024Personalized Text Generation with Fine-Grained Linguistic Controlcited by 20
- 2025Personalized Graph-Based Retrieval for Large Language Modelscited by 10
Built on by
Citing papers per year: 2026: 1.
1 paper.