allenai/CommonGen-Eval

Evaluating LLMs with CommonGen-Lite

31
/ 100
Emerging

This project helps evaluate how well different large language models (LLMs) can generate sentences from a given set of concepts. You input a list of nouns and verbs, and the system outputs a natural, common sentence created by an LLM that includes all those words. This is for researchers and developers working with LLMs who need to benchmark their models' constrained text generation abilities.

No commits in the last 6 months.

Use this if you are developing or fine-tuning an LLM and need to objectively measure its proficiency in generating coherent sentences that incorporate specific, provided concepts.

Not ideal if you are an end-user simply looking to generate text, as this tool focuses on comparative evaluation rather than direct text generation for content creation.

LLM evaluation natural language generation text generation quality constrained text synthesis model benchmarking
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

95

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Mar 21, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/allenai/CommonGen-Eval"

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