A Dual-Dimensional LLM Framework for Automated Item Incidental Content Similarity Analysis in Large-Scale Assessments
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
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via arxiv author · 85%Jiajing Huang →
“A Dual-Dimensional LLM Framework for Automated Item Incidental Content Similarity Analysis in Large-Scale Assessments”
- LinkedLinked via arxiv author · 85%Jihong Zhang →
“A Dual-Dimensional LLM Framework for Automated Item Incidental Content Similarity Analysis in Large-Scale Assessments”
- LinkedLinked via arxiv author · 85%Hua-Hua Chang →
“A Dual-Dimensional LLM Framework for Automated Item Incidental Content Similarity Analysis in Large-Scale Assessments”