RUCAIBox/LLMRank

[ECIR'24] Implementation of "Large Language Models are Zero-Shot Rankers for Recommender Systems"

42
/ 100
Emerging

This project helps e-commerce managers, content curators, or anyone managing a recommendation system to quickly evaluate how Large Language Models (LLMs) can rank items for users without needing to train a new model. You provide user interaction histories and a list of candidate items, and it uses an LLM to generate a personalized ranking of those items. The output is a ranked list of recommendations, which you can then use to improve your system's performance.

317 stars. No commits in the last 6 months.

Use this if you want to explore the potential of LLMs for personalized item ranking in your recommender system, especially for quick, zero-shot evaluations without extensive model training.

Not ideal if you prefer to build traditional, domain-specific ranking models from scratch or if you need to deploy a highly optimized, low-latency ranking solution without reliance on external LLM APIs.

e-commerce recommendation-systems content-personalization item-ranking user-engagement
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

317

Forks

28

Language

Python

License

MIT

Last pushed

May 15, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/RUCAIBox/LLMRank"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.