Hyun-Ryu/clover

Official code for "Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoning", ICLR 2025.

27
/ 100
Experimental

This project helps evaluate and improve how large language models (LLMs) interpret and reason about complex logical statements written in natural language. It takes natural language text containing logical puzzles or problems, translates them into precise first-order logic formulas, and then verifies their accuracy. The primary user would be researchers or practitioners working on developing and testing advanced AI systems that require robust logical reasoning capabilities.

No commits in the last 6 months.

Use this if you are developing or evaluating LLMs and need to rigorously test their ability to translate complex natural language logic into formal logical expressions and verify the consistency of their reasoning.

Not ideal if you are looking for a general-purpose natural language processing tool or an LLM application for everyday tasks that do not involve formal logical reasoning.

AI-research logical-reasoning LLM-evaluation neurosymbolic-AI formal-logic
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

27

Forks

3

Language

Python

License

Last pushed

May 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Hyun-Ryu/clover"

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