itayle/diverse-demonstrations

Diverse Demonstrations Improve In-context Compositional Generalization

19
/ 100
Experimental

This project helps researchers working with large language models improve how these models generalize to new, complex instructions. By carefully selecting a diverse set of examples to show the model, rather than just similar ones, it helps the model learn to construct new logical structures. This is particularly useful for AI researchers and machine learning engineers developing more robust semantic parsing or natural language understanding systems.

No commits in the last 6 months.

Use this if you are an AI researcher or machine learning engineer struggling with large language models failing to generalize to new, unseen compositional structures in tasks like semantic parsing.

Not ideal if you are a practitioner looking for a ready-to-use, off-the-shelf solution for general natural language processing tasks without deep involvement in model training.

AI research natural language understanding large language models semantic parsing compositional generalization
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 6 / 25

How are scores calculated?

Stars

12

Forks

1

Language

Python

License

Last pushed

Jul 07, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/itayle/diverse-demonstrations"

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