rahmanidashti/SyntheticTestCollections

[Official Codes] Synthetic Test Collections for Retrieval Evaluation (SIGIR 2024)

13
/ 100
Experimental

This project helps researchers and practitioners evaluate information retrieval (IR) systems by creating synthetic test collections. It takes existing documents and uses Large Language Models (LLMs) to generate new user queries and determine how relevant documents are to those queries, producing a complete test set. Information retrieval researchers, search engine developers, and anyone involved in assessing IR system performance would use this.

No commits in the last 6 months.

Use this if you need to evaluate an information retrieval system but face challenges in acquiring diverse user queries and costly manual relevance judgments.

Not ideal if you already have access to extensive, human-generated test collections and relevance judgments, or if you specifically require evaluating systems only with real user data.

information-retrieval search-engine-evaluation test-data-generation llm-applications academic-research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

11

Forks

Language

License

Last pushed

Jul 19, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/rahmanidashti/SyntheticTestCollections"

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