GAIR-NLP/scaleeval

Scalable Meta-Evaluation of LLMs as Evaluators

23
/ 100
Experimental

This tool helps AI product managers and researchers determine which large language models (LLMs) are best at evaluating the quality of other LLMs. You input various LLM responses, specific evaluation criteria (like creativity or helpfulness), and different scenarios. The tool then outputs a ranked assessment of how well different LLMs perform as evaluators, based on a debate simulation.

No commits in the last 6 months.

Use this if you need to reliably select the best LLM to serve as an automated judge for the outputs of other LLMs.

Not ideal if you're looking for an LLM to generate content or perform direct tasks rather than evaluate other models.

LLM evaluation AI product management model selection AI research quality assessment
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 7 / 25

How are scores calculated?

Stars

43

Forks

3

Language

Python

License

Last pushed

Feb 15, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/GAIR-NLP/scaleeval"

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