VITA-Group/Ms-PoE

"Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding" Zhenyu Zhang, Runjin Chen, Shiwei Liu, Zhewei Yao, Olatunji Ruwase, Beidi Chen, Xiaoxia Wu, Zhangyang Wang.

34
/ 100
Emerging

This project helps improve how Large Language Models (LLMs) find and use important details when they're given a very long piece of text. It takes an existing LLM and enhances its ability to pinpoint relevant information, especially if that information is buried in the middle of a long document or conversation. Researchers and AI engineers working with LLMs for complex tasks like summarization or long-form Q&A would find this useful.

No commits in the last 6 months.

Use this if your Large Language Models struggle to accurately extract or act upon key information located in the middle of extremely long text inputs.

Not ideal if you are not working with Large Language Models or if your primary concern is not long-context understanding.

Large Language Models NLP research long-context understanding information retrieval AI model improvement
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

31

Forks

4

Language

Python

License

MIT

Last pushed

May 07, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/VITA-Group/Ms-PoE"

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