zorazrw/filco

[Preprint] Learning to Filter Context for Retrieval-Augmented Generaton

40
/ 100
Emerging

This tool helps improve the accuracy and relevance of answers generated by AI systems, especially for question-answering tasks. It takes a question and a collection of retrieved text passages, then intelligently filters out less relevant information. The output is a refined set of passages that helps the AI generate more precise answers. It's for researchers and practitioners working on fine-tuning large language models for specific generative AI applications.

196 stars. No commits in the last 6 months.

Use this if you are building or fine-tuning a retrieval-augmented generation (RAG) system and want to reduce 'hallucinations' or irrelevant information in the generated output.

Not ideal if you are looking for a ready-to-use, off-the-shelf generative AI application or if you don't have experience with training and evaluating large language models.

generative-AI natural-language-processing question-answering-systems large-language-models information-retrieval
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

196

Forks

20

Language

Python

License

CC-BY-SA-4.0

Last pushed

Apr 06, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/zorazrw/filco"

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