Logic-of-Thought uses few-shot LLM prompting to convert puzzle descriptions into answer set programs, then solves them with Clingo, achieving near-perfect accuracy on seven puzzle tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Logic-of-Thought: Empowering Large Language Models with Logic Programs for Solving Puzzles in Natural Language
Logic-of-Thought uses few-shot LLM prompting to convert puzzle descriptions into answer set programs, then solves them with Clingo, achieving near-perfect accuracy on seven puzzle tasks.