Value-Spectrum：通过社交媒体语境中的价值分解量化视觉-语言模型的偏好
Value-Spectrum: Quantifying Preferences of Vision-Language Models via Value Decomposition in Social Media Contexts
AI总结：
本文提出Value-Spectrum基准，基于Schwartz价值维度构建超5万条社交媒体短视频的VQA数据集，用于量化视觉-语言模型的价值偏好并评估其角色扮演适应性。
摘要：
视觉-语言模型（VLMs）的最新进展拓宽了多模态应用的范围。然而，评估往往仍局限于功能性任务，忽视了人格特质和人类价值观等抽象维度。为弥补这一不足，我们提出了Value-Spectrum，一个新颖的视觉问答（VQA）基准，旨在基于Schwartz价值维度评估VLMs，这些维度捕捉了引导人们偏好和行动的核心人类价值观。我们设计了一个VLM智能体流水线来模拟视频浏览，并构建了一个向量数据库，其中包含来自TikTok、YouTube Shorts和Instagram Reels的超过50,000个短视频。这些视频跨越数月，涵盖家庭、健康、爱好、社会、技术等多种主题。在Value-Spectrum上的基准测试凸显了VLMs处理价值导向内容时的显著差异。除了识别VLMs的内在偏好外，我们还探索了VLM智能体在明确提示下采用特定人设的能力，揭示了模型在角色扮演场景中的适应性。这些发现凸显了Value-Spectrum作为一个全面评估集的潜力，可用于追踪VLMs在基于价值的任务中的偏好以及模拟多样化人设的能力。完整代码和数据可在以下地址获取：https://github.com/Jeremyyny/Value-Spectrum。
英文摘要：
The recent progress in Vision-Language Models (VLMs) has broadened the scope of multimodal applications. However, evaluations often remain limited to functional tasks, neglecting abstract dimensions such as personality traits and human values. To address this gap, we introduce Value-Spectrum, a novel Visual Question Answering (VQA) benchmark aimed at assessing VLMs based on Schwartz's value dimensions that capture core human values guiding people's preferences and actions. We design a VLM agent pipeline to simulate video browsing and construct a vector database comprising over 50,000 short videos from TikTok, YouTube Shorts, and Instagram Reels. These videos span multiple months and cover diverse topics, including family, health, hobbies, society, technology, etc. Benchmarking on Value-Spectrum highlights notable variations in how VLMs handle value-oriented content. Beyond identifying VLMs' intrinsic preferences, we also explore the ability of VLM agents to adopt specific personas when explicitly prompted, revealing insights into the adaptability of the model in role-playing scenarios. These findings highlight the potential of Value-Spectrum as a comprehensive evaluation set for tracking VLM preferences in value-based tasks and abilities to simulate diverse personas. The complete code and data are available at: https://github.com/Jeremyyny/Value-Spectrum.
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。
