A content-based recommender that builds user profiles from LLM-written short-term and long-term summary texts, fuses them with attention, and claims modest ranking gains plus built-in textual explanations.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Explainable Temporal User Profiling with LLMs
A content-based recommender that builds user profiles from LLM-written short-term and long-term summary texts, fuses them with attention, and claims modest ranking gains plus built-in textual explanations.