aiqbench analysis
This paper presents CLARER, a recommendation model that fuses rating data with aspect-based semantic features from text reviews using contrastive learning and transformer encoders. By integrating these signals, the framework enhances both prediction accuracy and the ability to generate interpretable explanations for user preferences. The approach demonstrates superior performance on standard benchmarks while addressing the explainability gap in modern recommender systems.
Contrastive Learning for Aspect Representation towards Explainable Recommendation
arXiv:2610.07761v1 Announce Type: cross Abstract: In this work, we propose a novel recommendation model, CLARER (Contrastive Learning for Aspect Representation towards Explainable Recommendation) that integrates aspect features learned from textual reviews with rating information to improve the accuracy and explainability of recommendations. Our proposed framework learns user and item representations by combining rating-based features and aspect-based features from reviews. Specifically, rating-based features are learned through a multi-layer perceptron (MLP) model, while aspect-specific review representations are learned using a transformer encoder to capture the semantic information and contrastive learning to better distinguish user preferences. To provide explanations, we train a transformer decoder, using the final representations of users and items from both rating and aspect-based features as context. Experimental results in three benchmark data sets demonstrate that our model achieves superior performance compared to baseline methods in both recommendation (accuracy) and explanation generation.
Abstract:In this work, we propose a novel recommendation model, CLARER (Contrastive Learning for Aspect Representation towards Explainable Recommendation) that integrates aspect features learned from textual reviews with rating information to improve the accuracy and explainability of recommendations. Our proposed framework learns user and item representations by combining rating-based features and aspect-based features from reviews. Specifically, rating-based features are learned through a multi-layer perceptron (MLP) model, while aspect-specific review representations are learned using a transformer encoder to capture the semantic information and contrastive learning to better distinguish user preferences. To provide explanations, we train a transformer decoder, using the final representations of users and items from both rating and aspect-based features as context. Experimental results in three benchmark data sets demonstrate that our model achieves superior performance compared to baseline methods in both recommendation (accuracy) and explanation generation.
8 pages. Published in WI-IAT 2025. Best Student Paper Award
Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)
arXiv:2610.07761 [cs.IR]
(or arXiv:2610.07761v1 [cs.IR] for this version)
https://doi.org/10.48550/arXiv.2610.07761 arXiv-issued DOI via DataCite (pending registration)
E. Hasan and C. Ding, "Contrastive Learning for Aspect Representation Towards Explainable Recommendation," 2025 IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT), pp. 483-490, 2025
https://doi.org/10.1109/WI-IAT67162.2025.00070 DOI(s) linking to related resources
Full text under the publisher's open licence · 202 words
Related coverage
Deconfusing Corrigibility
AI Alignment Forum · Oct 17, 2026
Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics
Latent Space · Oct 13, 2026
Koopman Theory and Metaethics
LessWrong · Sep 19, 2026
What can language models teach us about understanding?
LessWrong · Oct 9, 2026