LivingFutureLab/UQABench

[KDD 2025] The source code for UQABench

26
/ 100
Experimental

This benchmark helps e-commerce platforms and personalized recommendation systems evaluate how well their large language models (LLMs) can answer customer questions in a personalized way. It takes historical user interaction data, like past purchases or clicks, and outputs metrics showing how accurately an LLM can provide tailored answers. This is for researchers and engineers working on enhancing personalized customer service or product recommendations.

No commits in the last 6 months.

Use this if you need a standardized way to test and compare different methods of personalizing LLM responses for individual users based on their historical behavior.

Not ideal if you are looking for a plug-and-play LLM solution or a general-purpose question-answering system without a strong focus on user personalization benchmarks.

e-commerce personalized-recommendations customer-experience AI-evaluation LLM-benchmarking
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

13

Forks

2

Language

Python

License

Last pushed

Aug 18, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/LivingFutureLab/UQABench"

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