Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This study employs a fine-tuned multimodal large language model (LLM) based on Qwen3.5 to reconstruct multiple-choice model (MCM) and three-parameter logistic (3PL) model curves by simulating response probabilities. By training the model on a diverse corpus of multiple-choice items with both text and image stimuli, conditioned on student ability levels, the LLM captures the systematic error patterns of students, enabling it to approximate item difficulty effectively. The key finding reveals that the model can accurately predict option probabilities, demonstrating a novel approach to item parameter estimation in educational assessments.
Fine-tuning a multimodal LLM can unlock precise item difficulty estimates from student response patterns, transforming assessment design.
We present results from reconstructing multiple-choice model (MCM) and three-parameter logistic (3PL) model curves using a fine-tuned multimodal large language model (LLM) based on Qwen3.5. The model is prompted and fine-tuned to replicate choice probabilities across a large training corpus of multiple-choice items containing both image and text stimuli, conditioned on a labeled set of student ability levels. By learning to reproduce the systematic error patterns of students across a discrete range of abilities, the LLM implicitly captures the underlying response probabilities encoded in the 3PL and MCM curves. This allows us to accurately approximate item difficulty on a held-out test set directly from the model's predicted option probabilities.