Combining Formal Reasoning and LLMs for Scenario-Based Educational STEM Exercises

Abstract excerpt

<title>Abstract</title> <p>Large language models (LLMs) enable scalable generation of exercises for science, technology, engineering, and mathematics (STEM) but often produce mathematically invalid or physically inconsistent problems, while manual authoring remains accurate but hard to scale. This paper introduces a neuro‑symbolic framework for scenario‑centric STEM exercise generation, demonstrated on introducto...

Topics

Open a Topic to create a Post that cites this publication.

• Genetic Code
• Human Genome Project
• Immunoglobulins
• Molecular Biology
• Mutation

Identifiers and source

Literature Corpus work

3a2668f5-9aac-56f7-ad9e-e9a3ce36bac7

DOI

10.21203/rs.3.rs-8989074/v1