GeorgeVern/lmcor

Code for the EACL 2024 paper: "Small Language Models Improve Giants by Rewriting Their Outputs"

19
/ 100
Experimental

LM-Corrector helps improve the quality of text generated by large language models for tasks like summarization, translation, or grammatical error correction. It takes multiple text outputs from an existing LLM as input and then refines them into a single, higher-quality output. This tool is for AI researchers and practitioners who want to get better results from their language models.

No commits in the last 6 months.

Use this if you are using large language models for text generation tasks and want to significantly improve the accuracy and fluency of their outputs without retraining the original LLM.

Not ideal if you need a pre-trained, ready-to-use application, as this project requires technical setup and model training.

natural-language-processing large-language-models text-generation machine-translation summarization
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

Apr 20, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/GeorgeVern/lmcor"

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