PREFER: Personalized Review Summarization with Online Preference Learning
Abstract
Product reviews significantly influence purchasing decisions on e-commerce platforms. However, the sheer volume of reviews can overwhelm users, obscuring information most relevant to their individual needs. Existing e-commerce summarization systems typically produce generic, static summaries that fail to account for the fact that (i) different users prioritize different product characteristics, and (ii) these preferences may evolve with interactions. To address these challenges, we propose an online learning framework that generates personalized summaries for each user by representing user interests in a latent aspect space and selecting preference-aligned review evidence. Our system then iteratively refines its understanding of user preferences by incorporating feedback on the generated summaries directly over time. We evaluate our framework on Amazon Reviews'23 using controlled feedback simulations and robustness checks with held-out-history, independent-embedding, and external LLM-based evaluators. These experiments show improvements in preference-aligned evidence selection under the evaluated feedback settings. A separate human-based study finds that scenario-conditioned summaries are preferred over generic (uniformly-aggregated) alternatives in 69.9% of paired comparisons.
Related
- Chance-Constrained Personalized LLM Routing with Online Preference Learning
- Reliability-Weighted Direct Preference Optimization: Penalized Weights for Robust Preference Learning
- Augmented Patient Preference Incorporated Reinforcement Learning (APP-RL) to Estimate the Optimal Dynamic Treatment Regime
- Learning in Continuous Games from Pairwise Preference Feedback
- Targeted Active Learning for Preference-Based Treatment Effects on Multivariate Outcomes
BibTeX
@misc{roy2026prefer,
title = {{PREFER: Personalized Review Summarization with Online Preference Learning}},
author = {Millend Roy and Agostino Capponi and Vineet Goyal},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2605.05911},
eprint = {2605.05911},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.05911},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - PREFER: Personalized Review Summarization with Online Preference Learning
AU - Millend Roy
AU - Agostino Capponi
AU - Vineet Goyal
PY - 2026
DA - 2026/10/26
PB - arXiv
DO - 10.48550/arxiv.2605.05911
UR - https://arxiv.org/abs/2605.05911
AB - Product reviews significantly influence purchasing decisions on e-commerce platforms. However, the sheer volume of reviews can overwhelm users, obscuring information most relevant to their individual needs. Existing e-commerce summarization systems typically produce generic, static summaries that fail to account for the fact that (i) different users prioritize different product characteristics, and (ii) these preferences may evolve with interactions. To address these challenges, we propose an online learning framework that generates personalized summaries for each user by representing user interests in a latent aspect space and selecting preference-aligned review evidence. Our system then iteratively refines its understanding of user preferences by incorporating feedback on the generated summaries directly over time. We evaluate our framework on Amazon Reviews'23 using controlled feedback simulations and robustness checks with held-out-history, independent-embedding, and external LLM-based evaluators. These experiments show improvements in preference-aligned evidence selection under the evaluated feedback settings. A separate human-based study finds that scenario-conditioned summaries are preferred over generic (uniformly-aggregated) alternatives in 69.9% of paired comparisons.
ER -