sdpkjc/SATQuest

🏞 A Verifier for Logical Reasoning Evaluation and Reinforcement Fine-Tuning of LLMs

30
/ 100
Emerging

This project helps evaluate and improve the logical reasoning abilities of large language models (LLMs). It takes problem definitions, such as Boolean satisfiability (SAT) formulas, and generates various question formats. It then verifies the LLM's answers, providing a score and diagnostics to help developers understand and fine-tune their models for better logical performance. This is for AI researchers and developers working on building and refining LLMs that need to excel at complex logical tasks.

No commits in the last 6 months. Available on PyPI.

Use this if you are developing or evaluating LLMs and need a robust framework to test and improve their ability to solve logical reasoning problems, particularly those based on Conjunctive Normal Form (CNF).

Not ideal if you are not working with LLMs or their logical reasoning capabilities, or if your primary need is for a general-purpose SAT solver rather than an LLM evaluation tool.

LLM evaluation AI research logical reasoning model fine-tuning natural language processing
Stale 6m
Maintenance 2 / 25
Adoption 4 / 25
Maturity 24 / 25
Community 0 / 25

How are scores calculated?

Stars

5

Forks

Language

Python

License

MIT

Last pushed

Sep 26, 2025

Commits (30d)

0

Dependencies

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/sdpkjc/SATQuest"

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