Using Large Language Models for (De-)Formalization and Natural Argumentation Exercises for Beginner's Students
arXiv:2304.06186v31 citationsh-index: 9
Originality Synthesis-oriented
AI Analysis
This addresses the need for scalable educational tools in logic and argumentation training for students, but it is incremental as it applies existing LLM methods to a new educational context.
The paper tackles the problem of automating correction for logic translation and natural argumentation exercises for beginner students, using large language models to develop two systems for these tasks.
We describe two systems currently being developed that use large language models for the automatized correction of (i) exercises in translating back and forth between natural language and the languages of propositional logic and first-order predicate logic and (ii) exercises in writing simple arguments in natural language in non-mathematical scenarios.