SOURCE-LINKED INTELLIGENCE

A Dual-Dimensional LLM Framework for Automated Item Incidental Content Similarity Analysis in Large-Scale Assessments

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

The rapid expansion of large-scale assessments and the growing adoption of automatic item generation have intensified concerns about incidental content redundancy, where construct-irrelevant elements such as wording or contextual framing become unintentionally repetitive across items. Traditional similarity metrics like BLEU or cosine similarity, often fail to capture the nuanced structural and semantic layers that drive perceived redundancy simultaneously. This study proposes a dual-dimensional framework for Automated Item Similarity Analysis (AISA) powered by Large Language Models (LLMs), op

Read original source ↗ Open in workspace

recordType

paper

region

Global