多模态大模型中可靠性优先的细粒度生成
Reliability-Prioritized Fine-Grained Generation in Multimodal Large
AI总结：
针对多模态大模型细粒度生成易出错的问题，提出GranFact基准和层次感知评估算法，并基于直接偏好优化提出可靠性优先的偏好优化方法，提升细粒度生成同时保持可靠性。
摘要：
多模态大语言模型（MLLMs）越来越需要生成视觉内容的细粒度描述。然而，我们观察到并从理论上证明，生成细粒度响应会带来可靠性挑战，即细粒度生成比粗粒度生成更容易出错。这一现象表明，模型应生成最可靠的最细粒度描述，而非简单地产生更具体的输出。为研究此问题，我们开发了GranFact，一个粒度感知基准，包含专家验证的多目标图像及其从粗到细的类别标注。然后，我们设计了一种层次感知评估算法，该算法既评估模型预测在视觉上是否正确，也评估正确预测的具体程度。我们还提出了一种基于直接偏好优化的可靠性优先偏好优化方法，该方法惩罚不可靠的细粒度断言，同时奖励可靠的细粒度。在GranFact上的实验表明，我们的方法在保持可靠性的同时改善了细粒度生成。代码和数据可在https://github.com/WeiWu2025/GranFact获取。
英文摘要：
Multimodal large language models (MLLMs) are increasingly expected to generate fine-grained descriptions of visual content. However, we observe and theoretically show that generating fine-grained responses poses a reliability challenge, \textit{i.e.}, fine-grained generation is more error-prone than coarse-grained generation. This phenomenon suggests that models should generate the finest description that remains reliable rather than simply produce more specific outputs. To investigate this problem, we develop \textsc{GranFact}, a granularity-aware benchmark consisting of expert-verified multi-object images with coarse-to-fine category annotations. Then, we design a hierarchy-aware evaluation algorithm, which assesses both whether model predictions are visually correct and how specific the correct predictions are. We also propose a reliability-prioritized preference optimization method based on Direct Preference Optimization, which penalizes unreliable fine-grained claims while rewarding reliable specificity. Experiments on \textsc{GranFact} show that our method improves fine-grained generation while preserving reliability. Code and data are available \href{https://github.com/WeiWu2025/GranFact}{here}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
