Can LLMs Model Incorrect Student Reasoning? A Case Study on Distractor Generation

2026-03-16

AI Summary

This study addresses the challenge of guiding large language models (LLMs) to effectively model students’ plausible misconceptions in problem-solving for the purpose of generating high-quality multiple-choice distractors. To this end, we develop an evaluation framework grounded in educational best practices, enabling fine-grained assessment of LLMs’ reasoning chains through structured behavioral analysis, misconception diagnosis, and prompt engineering. Our work is the first to systematically demonstrate a strong alignment between LLM-generated distractors and established pedagogical principles when simulating student errors, while identifying that model failures primarily stem from the correct-answer recovery and candidate filtering stages. Experimental results show that explicitly providing the correct answer in prompts increases the consistency between generated and human-authored distractors by 8%, underscoring the critical role of anchoring on the correct solution in modeling erroneous reasoning.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Cognitive Modeling & Cognitive Systems: Analogy

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Modeling plausible student misconceptions is critical for AI in education. In this work, we examine how large language models (LLMs) reason about misconceptions when generating multiple-choice distractors, a task that requires modeling incorrect yet plausible answers by coordinating solution knowledge, simulating student misconceptions, and evaluating plausibility. We introduce a taxonomy for analyzing the strategies used by state-of-the-art LLMs, examining their reasoning procedures and comparing them to established best practices in the learning sciences. Our structured analysis reveals a surprising alignment between their processes and best practices: the models typically solve the problem correctly first, then articulate and simulate multiple potential misconceptions, and finally select a set of distractors. An analysis of failure modes reveals that errors arise primarily from failures in recovering the correct solution and selecting among response candidates, rather than simulating errors or structuring the process. Consistent with these results, we find that providing the correct solution in the prompt improves alignment with human-authored distractors by 8%, highlighting the critical role of anchoring to the correct solution when generating plausible incorrect student reasoning. Overall, our analysis offers a structured and interpretable lens into LLMs' ability to model incorrect student reasoning and produce high-quality distractors.

Problem

• student misconceptions
• distractor generation
• large language models
• plausible reasoning
• AI in education

Innovation

• distractor generation
• student misconceptions
• large language models
• reasoning alignment
• AI in education