How Well Do LLMs Predict Prerequisite Skills? Zero-Shot Comparison to Expert-Defined Concepts

TL;DR

This paper evaluates whether large language models can predict prerequisite skills from natural language descriptions without fine-tuning, using a new benchmark dataset and multiple models, showing promising results for scalable skill modeling.

Contribution

It introduces ESCO-PrereqSkill, a benchmark dataset for zero-shot prediction of prerequisite skills, and systematically evaluates 13 LLMs, demonstrating their potential in this task.

Findings

LLaMA4-Maverick, Claude-3-7-Sonnet, and Qwen2-72B perform well in predicting prerequisites

Models show strong semantic reasoning capabilities without supervision

The approach supports scalable prerequisite skill modeling for educational applications

Abstract

Prerequisite skills - foundational competencies required before mastering more advanced concepts - are important for supporting effective learning, assessment, and skill-gap analysis. Traditionally curated by domain experts, these relationships are costly to maintain and difficult to scale. This paper investigates whether large language models (LLMs) can predict prerequisite skills in a zero-shot setting, using only natural language descriptions and without task-specific fine-tuning. We introduce ESCO-PrereqSkill, a benchmark dataset constructed from the ESCO taxonomy, comprising 3,196 skills and their expert-defined prerequisite links. Using a standardized prompting strategy, we evaluate 13 state-of-the-art LLMs, including GPT-4, Claude 3, Gemini, LLaMA 4, Qwen2, and DeepSeek, across semantic similarity, BERTScore, and inference latency. Our results show that models such as LLaMA4-Maverick, Claude-3-7-Sonnet, and Qwen2-72B generate predictions that closely align with expert ground truth, demonstrating strong semantic reasoning without supervision. These findings highlight the potential of LLMs to support scalable prerequisite skill modeling for applications in personalized learning, intelligent tutoring, and skill-based recommender systems.