paper-with-me

Papers

Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs

2026-06-10 · Shayan Mohammadizadehsamakosh, Pritam Sarkar, Leonid Sigal, Ali Etemad, Elham Dolatabadi arxiv

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) reliance on static supervised fine-tuning references as preferred responses introduces an off-policy distribution shift, steering optimization toward stylistic artifacts over clinical correctness; and (3) alignment objectives lack explicit visual grounding constraints, leaving models insensitive to subtle yet diagnostically decisive pathological features. Our method leverages a bidirectional token-wise KL regularizer alongside a visual-contrastive grounding objective that pairs clean and lesion-corrupted images to penalize responses generated without adequate visual evidence. Together, these components form a fine-grained, on-policy alignment framework that constructs preference pairs by minimally editing model-generated outputs, correcting only clinically erroneous spans while preserving the original linguistic style. Extensive experiments across medical imaging tasks and clinical text generation benchmarks validate the effectiveness of our approach.

📄 PDF Abstract BibTeX arXiv:2606.12590

Code (0)

등록된 구현이 없습니다.

Tasks

Visual GroundingText Generation

Similar Papers 제목 키워드 기반

CheXPO: Preference Optimization for Chest X-ray VLMs with Counterfactual Rationale

2025-07-09 · Xiao Liang, Jiawei Hu, Di Wang, Zhi Ma 외 arxiv

Vision-language models (VLMs) are prone to hallucinations that critically compromise reliability in medical applications. While preference optimization can mitigate these hallucinations through clinical feedback, its imp…

Hierarchical Divide-and-Conquer for Fine-Grained Alignment in LLM-Based Medical Evaluation

2025-01-12 · Shunfan Zheng, Xiechi Zhang, Gerard de Melo, Xiaoling Wang 외

In the rapidly evolving landscape of large language models (LLMs) for medical applications, ensuring the reliability and accuracy of these models in clinical settings is paramount. Existing benchmarks often focus on fixe…

AttributeMultiple-choice

Data Selection for LLM Alignment Using Fine-Grained Preferences

2025-08-11 · Jia Zhang, Yao Liu, Chen-Xi Zhang, Yi Liu 외 arxiv

Large language models (LLMs) alignment aims to ensure that the behavior of LLMs meets human preferences. While collecting data from multiple fine-grained, aspect-specific preferences becomes more and more feasible, exist…

ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning

2025-05-25 · Yeyuan Wang, Dehong Gao, Rujiao Long, Lei Yi 외

Direct Preference Optimization (DPO) has gained significant attention for its simplicity and computational efficiency in aligning large language models (LLMs). Recent advancements have extended DPO to multimodal scenario…

Computational EfficiencyMultimodal ReasoningSentence

ProMedical: Hierarchical Fine-Grained Criteria Modeling for Medical LLM Alignment via Explicit Injection

2026-04-09 · He Geng, Yangmin Huang, Lixian Lai, Qianyun Du 외 arxiv

Aligning Large Language Models (LLMs) with high-stakes medical standards remains a significant challenge, primarily due to the dissonance between coarse-grained preference signals and the complex, multi-dimensional natur…

Reinforcement Learning