Tackling the Root of Misinformation by Teaching Laypeople about Logical Fallacies via Socratic Questioning and Critical Argumentation

2026-05-31

AI Summary

This work addresses the challenge that logical fallacies in everyday discourse are often difficult for the general public to detect, a problem exacerbated by the potential misuse of large language models (LLMs) for disseminating misinformation at scale. To counter this, the paper introduces LFTutor, the first LLM-powered intelligent tutoring system that integrates intent-driven Socratic questioning with a critical argumentation framework. By guiding users to reflect on their own reasoning processes, LFTutor aims to enhance their ability to identify logical fallacies. Experimental results demonstrate that LFTutor significantly outperforms baseline models lacking this pedagogical strategy, both in automated evaluations and human assessments, effectively improving users’ argumentative competence and critical thinking skills.

Abstract

Identifying logical fallacies in everyday discourse is challenging for many people. This challenge is amplified in the era of Large Language Models (LLMs), where malicious agents can deploy fallacious arguments to disseminate misinformation at scale. In this work, we explore the potential of LLMs as part of the solution. We introduce LFTutor, an intelligent tutoring system which uses LLMs to tutor laypeople and help them learn about logical fallacies. LFTutor integrates intent-driven Socratic questioning and critical argumentation principles to actively engage learners to reflect on their reasoning. Through both automatic and human evaluations, we demonstrate that LFTutor significantly outperforms baseline LLMs lacking these pedagogical strategies. This work highlights the promise of combining LLMs with pedagogical scaffolding to foster critical thinking and argument literacy in the age of AI.

Problem

• logical fallacies
• misinformation
• critical thinking
• argument literacy
• laypeople

Innovation

• Socratic questioning
• critical argumentation
• logical fallacies
• intelligent tutoring system
• large language models