A General Multimodal Probing Framework for Data Fusion and Prediction with Frozen Large Language Models: Evidence from Multimodal EHR Data
A backbone-flexible probing framework that serializes structured electronic health record variables and leakage-pruned discharge-note sections into a shared frozen-LLM representation space and recovers primary diagnosis categories with linear probes, without fine-tuning the LLM is proposed.
Cheng-Yuan Liu, Xinyu Zhang, Yao Li et al.
· 0 citations