# A Framework for Human-AI Q-Matrix Refinement: A NeuralCDM Evaluation

arXiv: https://arxiv.org/abs/2604.16398 · HTML: https://mlsanity.com/paper/2604.16398/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 27 references that are in the map.
- First posted on arXiv 30 Mar 2026.

## Builds on (most cited first, 10 of 10)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Active Prompting with Chain-of-Thought for Large Language Models](https://mlsanity.com/paper/2302.12246/) (2023)
- [Neural Cognitive Diagnosis for Intelligent Education Systems](https://mlsanity.com/paper/1908.08733/) (2019)
- [Applying Large Language Models and Chain-of-Thought for Automatic Scoring](https://mlsanity.com/paper/2312.03748/) (2023)
- [AutoSCORE: Enhancing Automated Scoring with Multi-Agent Large Language Models via Structured Component Recognition](https://mlsanity.com/paper/2509.21910/) (2025)
- [Leveraging Large Language Models for Identifying Knowledge Components](https://mlsanity.com/paper/2511.09935/) (2025)

## Built on by (most cited first, 1 of 1)

- [Curriculum Brain: Constructing Curriculum Knowledge Graphs as a Substrate for Cognitive Diagnosis](https://mlsanity.com/paper/2610.05860/) (2026)

## Abstract (arXiv)

Q-matrices are a cornerstone of theory-driven assessment and learning analytics, making item demands and students' underlying knowledge components and misconceptions explicit and actionable. However, Q-matrices are typically crafted by experts, making them time-consuming to build, prone to subjectivity, and difficult to validate empirically. We propose a framework for human-AI Q-matrix refinement in which large language models (LLMs) generate candidate Q-matrices using structured, misconception-aware prompting, and NeuralCDM provides an empirical evaluation layer to compare candidates based on how well they explain student response data. We apply the framework to a thermodynamics assessment dataset and benchmark locally deployed LLMs against cloud-served models. Results show that iteratively refined LLM-generated Q-matrices can exceed expert-baseline model fit (AUC 0.780 vs. 0.717), and that locally deployed models achieve comparable performance to cloud APIs, supporting privacy-preserving deployment.