Nativeatom/FRoG

Fuzzy reasoning of Generalized Quantifiers (EMNLP 2024)

20
/ 100
Experimental

FRoG helps evaluate how well language models understand and reason with 'fuzzy' percentage terms like 'a small amount' or 'moderate' in real-world math problems. You input a math problem where a percentage is hidden, and a language model tries to select the most fitting fuzzy quantifier from a set of choices. This is used by researchers and developers who are building or testing large language models.

No commits in the last 6 months.

Use this if you are a researcher or developer who needs to assess the nuanced reasoning abilities of large language models, particularly their comprehension of imprecise numerical concepts.

Not ideal if you're looking for a tool to solve math problems directly or to convert fuzzy language into precise percentages for non-AI applications.

large-language-models natural-language-understanding AI-evaluation fuzzy-logic computational-linguistics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Python

License

Apache-2.0

Last pushed

Jan 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/Nativeatom/FRoG"

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