XRec and RLMRec
These are complementary approaches to LLM-based recommendation: XRec prioritizes interpretability through explicit explanations, while RLMRec focuses on leveraging LLM representations as feature embeddings, enabling them to be combined for systems that are both semantically rich and human-understandable.
About XRec
HKUDS/XRec
[EMNLP'2024] "XRec: Large Language Models for Explainable Recommendation"
This project helps e-commerce managers and content curators improve their recommendation systems by providing clear, human-readable explanations for why certain items are recommended to a user. It takes existing user and item profiles, along with past interactions, and generates a tailored explanation for each recommendation. This is ideal for anyone managing online product catalogs or content platforms who wants to increase user trust and engagement.
About RLMRec
HKUDS/RLMRec
[WWW'2024] "RLMRec: Representation Learning with Large Language Models for Recommendation"
This tool helps improve recommendation systems by using Large Language Models to understand user preferences and item characteristics. It takes existing user interaction data and rich textual descriptions (like product reviews or user bios), then processes them to generate sophisticated user and item profiles. The output is a more accurate and nuanced recommendation engine, beneficial for e-commerce managers, content strategists, or platform owners seeking to personalize user experiences.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work