SCORE retrieves similar users' behaviors, uses an LLM self-assessment to rerank them, and injects the top ones in natural language into an LLM prompt, improving recommendation accuracy on two datasets.
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
-
LLMs as Better Recommenders with Natural Language Collaborative Signals: A Self-Assessing Retrieval Approach
SCORE retrieves similar users' behaviors, uses an LLM self-assessment to rerank them, and injects the top ones in natural language into an LLM prompt, improving recommendation accuracy on two datasets.