# Using Vision + Language Models to Predict Item Difficulty

arXiv: https://arxiv.org/abs/2603.04670 · HTML: https://mlsanity.com/paper/2603.04670/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 18 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Builds on (most cited first, 3 of 3)

- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Measuring and predicting variation in the difficulty of questions about data visualizations](https://mlsanity.com/paper/2505.08031/) (2025)

## Abstract (arXiv)

This project investigates the capabilities of large language models (LLMs) to determine the difficulty of data visualization literacy test items. We explore whether features derived from item text (question and answer options), the visualization image, or a combination of both can predict item difficulty (proportion of correct responses) for U.S. adults. We use GPT-4.1-nano to analyze items and generate predictions based on these distinct feature sets. The multimodal approach, using both visual and text features, yields the lowest mean absolute error (MAE) (0.224), outperforming the unimodal vision-only (0.282) and text-only (0.338) approaches. The best-performing multimodal model was applied to a held-out test set for external evaluation and achieved a mean squared error of 0.10805, demonstrating the potential of LLMs for psychometric analysis and automated item development.