mukhal/PromptRank

[ACL 2023] Few-shot Reranking for Multi-hop QA via Language Model Prompting

31
/ 100
Emerging

This tool helps improve the accuracy of open-domain question-answering systems, especially for complex questions that require stitching together information from multiple documents. It takes a collection of potential document paths (sequences of documents relevant to a question) and an instruction, then uses a large language model to score and re-rank these paths. The output is a more accurately ordered list of document paths, which can lead to better answers for multi-hop questions. This would be used by researchers and developers building advanced QA systems.

Use this if you need to re-rank retrieved document paths to find the most relevant information for multi-hop questions, especially in zero- or few-shot scenarios.

Not ideal if you are looking for a complete end-to-end question-answering system rather than a component for re-ranking document paths.

question-answering information-retrieval natural-language-processing document-ranking
No License No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

27

Forks

3

Language

Python

License

Last pushed

Oct 19, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/mukhal/PromptRank"

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