NL2FOL: Translating Natural Language to First-Order Logic for Logical Fallacy Detection

arXiv:2405.02318v1 Announce Type: cross
Abstract: Logical fallacies are common errors in reasoning that undermine the logic of an argument. Automatically detecting logical fallacies has important applications in tracking misinformation and validating claims. In this paper, we design a process to reliably detect logical fallacies by translating natural language to First-order Logic (FOL) step-by-step using Large Language Models (LLMs). We then utilize Satisfiability Modulo Theory (SMT) solvers to reason about the validity of the formula and classify inputs as either a …

abstract applications arxiv cs.ai cs.cl cs.lg cs.lo design detection errors language logic misinformation natural natural language paper process reasoning tracking type undermine