LFTutor: Tutoring People about Logical Fallacies through Intent-based Socratic Questioning and Critical Argumentation

ACL ARR 2025 July Submission265 Authors

Abstract: Distinguishing logical fallacies (LFs) from fact-based opinions remains challenging for many people in everyday discourse. This challenge is amplified in the era of Large Language Models (LLMs), where malicious agents can deploy flawed arguments to disseminate misinformation at scale. In this work, we explore the potential of LLMs both as part of the problem and the solution. We introduce LFTutor, an intelligent tutoring system designed to improve LLMs’ ability in dialogue-based education on 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 such 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.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: educational applications

Contribution Types: NLP engineering experiment

Languages Studied: English

Reassignment Request Area Chair: This is not a resubmission

Reassignment Request Reviewers: This is not a resubmission

A1 Limitations Section: This paper has a limitations section.

A2 Potential Risks: Yes

A2 Elaboration: Appendix H.1

B Use Or Create Scientific Artifacts: Yes

B1 Cite Creators Of Artifacts: Yes

B1 Elaboration: Appendix B

B2 Discuss The License For Artifacts: Yes

B2 Elaboration: Appendix H.2

B3 Artifact Use Consistent With Intended Use: Yes

B3 Elaboration: Appendix H.3, H.4

B4 Data Contains Personally Identifying Info Or Offensive Content: Yes

B4 Elaboration: Appendix H.6

B5 Documentation Of Artifacts: Yes

B5 Elaboration: Appendix H.5

B6 Statistics For Data: Yes

B6 Elaboration: Section 5.3, Section 6.1, Appendix A, Appendix B

C Computational Experiments: Yes

C1 Model Size And Budget: Yes

C1 Elaboration: Appendix A.6

C2 Experimental Setup And Hyperparameters: Yes

C2 Elaboration: Section 5.3, Section 6.1, and Appendix A.4

C3 Descriptive Statistics: Yes

C3 Elaboration: Section 5.3, Section 5.4, Section 6.1, Section 6.2, Section 6.3

C4 Parameters For Packages: Yes

C4 Elaboration: Section 6.1

D Human Subjects Including Annotators: Yes

D1 Instructions Given To Participants: Yes

D1 Elaboration: Appendix G.2, G.3

D2 Recruitment And Payment: Yes

D2 Elaboration: Appendix G.1, Appendix H.7

D3 Data Consent: Yes

D3 Elaboration: Appendix H.7

D4 Ethics Review Board Approval: Yes

D4 Elaboration: Appendix H.8

D5 Characteristics Of Annotators: Yes

D5 Elaboration: Appendix G.4

E Ai Assistants In Research Or Writing: Yes

E1 Information About Use Of Ai Assistants: Yes

E1 Elaboration: Appendix H.9

Author Submission Checklist: yes

Submission Number: 265