Pith. sign in

REVIEW 4 cited by

Biomedical Visual Instruction Tuning with Clinician Preference Alignment

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.13173 v3 pith:IXSFN6KF submitted 2024-06-19 cs.CV cs.AIcs.CLcs.LG

classification cs.CVcs.AIcs.CLcs.LG
keywords datainstructionclinicianmodelstuningvisualbiomedicaldatasets
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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 BioMed-VITAL.github.io.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis

    cs.LG 2025-06 conditional novelty 6.0 of 10

    SynthRL synthesizes harder, answer-preserving visual math questions from easy seed questions and reports small but mixed out-of-domain RLVR gains for Qwen2.5-VL-7B.

  2. EQPO: Equitable Group Relative Policy Optimization for Clinical Reasoning

    cs.LG 2025-10 reject novelty 5.0 of 10

    A GRPO variant that scales advantages by group size and mean reward is claimed to reduce demographic F1 gaps in clinical VLLMs, but the abstract and body report different experiments and the body's own tables contradi...

  3. Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models

    cs.CV 2025-07 reject novelty 4.0 of 10

    Expert-CFG combines entropy-based uncertainty selection with classifier-free guidance over expert-highlighted text to refine MedVLM outputs, reporting gains on VQA-RAD, SLAKE, and PathVQA.

  4. From large language models to multimodal AI: A scoping review on the potential of generative AI in medicine

    cs.AI 2025-02 conditional novelty 3.0 of 10

    A PRISMA-ScR scoping review of 144 studies finds the field shifting from text-only LLMs to multimodal AI in medicine, with evaluation and data diversity still the main bottlenecks.

Pith tools