Article

Optimizing GPT-Based Distractor Generation for the Korean CSAT English Exam

2025-09-18

Abstract excerpt

<title>Abstract</title> <p>High-quality distractors are essential in multiple-choice questions to assess student understanding and diagnose misconceptions; however, constructing these distractors manually is labor-intensive. This study presents the first large-scale investigation of automated distractor generation (ADG) for the English section of Korea’s College Scholastic Ability Test (CSAT), a high-stakes exam...

Topics

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

Identifiers and source

Literature Corpus work: 2a8a7cbf-8931-5b54-91c1-08ba8b155d55
DOI: 10.21203/rs.3.rs-6680435/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Optimizing GPT-Based Distractor Generation for the Korean CSAT English ExamDOI 10.21203/rs.3.rs-6680435/v1Read

Predicting Item-Level Characteristics of Knowledge Tests Using Large-Language ModelsSemantic proximity Read

Looks good on paper: LLM-generated exams are face-valid but psychometrically weaker than human assessmentsSemantic proximity Read

Field-testing multiple-choice questions with AI examinees: English grammar itemsSemantic proximity Read

Chat-WanJuan: A Fine-Tuned Compact Language Model for Multiple- Choice Question Generation in Medical EducationSemantic proximity Read

A Hybrid Transformer-Driven and Embedding-Augmented Framework for Automated Contextual MCQ Generation with Semantic Distractor Engineering and Difficulty-Aware ClassificationSemantic proximity Read

Generating Better Items for Cognitive Assessments Using Large Language ModelsSemantic proximity Read

Fine-Tuning PHI-3 for Multiple-Choice Question Answering: Methodology, Results, and ChallengesSemantic proximity Read

QUEST-AI: A System for Question Generation, Verification, and Refinement using AI for USMLE-Style ExamsSemantic proximity Read

MISP-Bench: Decomposing User-Provided False Priors into Answer, Rationale, and Guard EffectsSemantic proximity Read

Quality assurance and validity of AI-generated Single Best Answer questionsSemantic proximity Read

Can GPT-4 Replace Human Examiners? A Competition on Checking Open-Text AnswersSemantic proximity Read

Expert validation of AI-generated clinical assessment items for physician assistant certification: a multi-dimensional rubric and dual- reliability methodSemantic proximity Read