GiovanniTRA/UDCG

Code and Data of the paper: "Redefining Retrieval Evaluation in the Era of LLMs"

30
/ 100
Emerging

This helps AI researchers and developers evaluate how effectively a set of retrieved passages assists a large language model (LLM) in answering a question. You provide a list of questions, potential answer passages for each, and indicate which passages are relevant. The tool then calculates a 'Utility and Distraction-aware Cumulative Gain' (UDCG) score, indicating the overall quality of the passages for that specific LLM.

Use this if you need to quantitatively measure the quality of retrieved information for your LLM-powered question-answering systems.

Not ideal if you are looking for a tool to generate relevance labels or passages, or if your evaluation doesn't involve language models.

LLM evaluation Retrieval-Augmented Generation (RAG) Natural Language Processing (NLP) AI research context quality assessment
No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 13 / 25
Community 6 / 25

How are scores calculated?

Stars

12

Forks

1

Language

Python

License

MIT

Last pushed

Oct 27, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/GiovanniTRA/UDCG"

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