Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs
Large Vision-Language Models (LVLMs) have achieved strong performance across medical imaging tasks, yet they remain prone to factual inconsistencies, poor visual grounding, and misalignment with clinically meaningful feedback. Existing post-training alignment approaches, including Direct Preference Optimization (DPO) and its variants, face three critical limitations in the medical domain: (1) sequence-level reward signals treat clinically critical tokens identically to generic filler text; (2) r
Record details
Published: 10 June 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Healthcare
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Making Foresight Actionable: Repurposing Representation Alignment in World Action Models
arXiv · 10 June 2026
Fusion is not one-size-fits-all: Cross-Modal Representation Alignment for Time-to-Event Modeling
arXiv · 13 June 2026
Landmark-free Assessment of Lower-limb Alignment with Implicit Neural Shape Functions from Knee Radiographs
arXiv · 13 June 2026
Explaining Black-Box Language Models: Learning to Optimize Linguistically-Structured Word Subsets
arXiv · 7 June 2026
The Governance of Human-LLM Interaction: Safety Gating, Civility Steering, and Affective Default Lock-In
arXiv · 6 June 2026
LCAM: A Framework for Diagnosing Interactional Alignment Failures in Con-versational AI
arXiv · 6 June 2026
How to cite this record
ethics.ai (10 June 2026), “Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs,” evidence record 1134, https://ethics.ai/record/1134 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.