Biomedical Visual Instruction Tuning with Clinician Preference Alignment

Hejie Cui, Lingjun Mao, Xin LIANG, Jieyu Zhang, Hui Ren, Quanzheng Li, Xiang Li, Carl Yang

Keywords: resource-constrained human preference alignment, biomedical visual instruction tuning, instructioin data generation and selection

TL;DR: We propose a data-centric framework that incorporates clinician preferences into both stages of generating and selecting instruction data for tuning biomedical multimodal foundation models.

Abstract: Recent advancements in multimodal foundation models have showcased impressive capabilities in understanding and reasoning with visual and textual information. Adapting these foundation models trained for general usage to specialized domains like biomedicine requires large-scale domain-specific instruction datasets. While existing works have explored curating such datasets automatically, the resultant datasets are not explicitly aligned with domain expertise. In this work, we propose a data-centric framework, Biomedical Visual Instruction Tuning with Clinician Preference Alignment (BioMed-VITAL), that incorporates clinician preferences into both stages of generating and selecting instruction data for tuning biomedical multimodal foundation models. First, during the generation stage, we prompt the GPT-4V generator with a diverse set of clinician-selected demonstrations for preference-aligned data candidate generation. Then, during the selection phase, we train a separate selection model, which explicitly distills clinician and policy-guided model preferences into a rating function to select high-quality data for medical instruction tuning. Results show that the model tuned with the instruction-following data from our method demonstrates a significant improvement in open visual chat (18.5% relatively) and medical VQA (win rate up to 81.73%). Our instruction-following data and models are available at https://BioMed-VITAL.github.io.

Submission Number: 1823