Free Reads
Sign in to view your remaining parses.
Tag Filter
User Preference Modeling
SCREEN: A Benchmark for Situated Conversational Recommendation
Published:7/20/2024
Situated Conversational Recommendation SystemsMultimodal Large Language ModelConversational Recommendation BenchmarkUser Preference ModelingSituated Item Representation
The paper introduces Situated Conversational Recommendation Systems (SCRS) and presents the SCREEN dataset, which contains over 20,000 dialogues generated by multimodal large language models, simulating userrecommender interactions. This resource enriches future research in scen
05
InfoDCL: Informative Noise Enhanced Diffusion Based Contrastive Learning
Published:12/18/2025
Diffusion Model Contrastive LearningContrastive Learning in Recommendation SystemsUser Preference ModelingGraph Convolutional Network InferenceInformative Noise Enhancement
InfoDCL introduces a novel framework that combines a singlestep diffusion process with auxiliary semantic information to generate authentic user preferences, enhancing contrastive learning. It transforms interference between generation and preference learning into collaboration,
05
Pearl: A Review-driven Persona-Knowledge Grounded Conversational Recommendation Dataset
Published:8/1/2024
Conversational Recommendation SystemsLLM-based Recommendation DatasetPersonalized Recommendation DatasetUser Preference ModelingKnowledge-Augmented Conversational Recommendation
The PEARL dataset addresses limitations in conversational recommendation systems by providing specific user preferences and explanations. Synthesized from real reviews, it includes over 57k dialogues, enabling more contextually relevant recommendations. Models trained on PEARL ou
07
From IDs to Semantics: A Generative Framework for Cross-Domain Recommendation with Adaptive Semantic Tokenization
Published:11/11/2025
Cross-Domain Recommendation SystemGenerative Cross-Domain Recommendation FrameworkDomain-Adaptive TokenizationUser Preference ModelingMulti-Domain Joint Training
This paper presents GenCDR, a novel generative crossdomain recommendation framework that overcomes limitations of traditional methods by using domainadaptive tokenization for disentangled semantic IDs, significantly improving recommendation accuracy and generalization across mu
09