SVBench：视频生成模型的社会推理评测
SVBench: Evaluation of Video Generation Models on Social Reasoning
为视频生成模型提供了一个可复用的社会推理评测框架：用免训练的 agent 流水线把心理学范式转成视频场景，再用 VLM 作为评判器按五个可解释维度打分，可直接用于诊断生成模型在因果与心理动态上的缺陷。
原文依据 we introduce the first benchmark for social reasoning in video generation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期文本到视频生成模型在视觉真实感、运动保真度和文本-视频对齐方面取得了显著进展，但仍难以生成社会性连贯的行为。人类能够从简短的视觉线索中轻易推断意图、信念、情绪与社会规范，而当前模型往往只生成字面场景，未能捕捉背后的因果与心理动态。为系统评估这一局限，我们提出了首个面向视频生成中社会推理的基准。该基准植根于发展心理学与社会心理学，涵盖三十个经典社会认知范式，横跨七个核心维度：心理状态推断、目标导向行为、共同注意、社会协调、亲社会行为、社会规范与多智能体策略。为将这些范式付诸实施，我们构建了一个完全免训练的基于智能体的流水线，它提炼每个范式的推理结构、合成多样化的视频就绪场景、通过基于线索的评审来保证概念中立性与难度控制，并使用高容量 VLM 评判器沿五个可解释的社会推理维度对生成视频进行评估。借助该框架，我们对七个最优视频生成系统开展了首次大规模评测。结果表明，表面合理性同更深层的社会推理之间存在明显差距，说明当前模型在生成具有社会根基的行为方面仍然能力有限。https://github.com/Gloria2tt/SVBench-Evaluation
英文原文摘要 1561 字符
Recent text-to-video generation models have made remarkable progress in visual realism, motion fidelity, and text-video alignment, yet they still struggle to produce socially coherent behavior. Unlike humans, who readily infer intentions, beliefs, emotions, and social norms from brief visual cues, current models often generate literal scenes without capturing the underlying causal and psychological dynamics. To systematically assess this limitation, we introduce the first benchmark for social reasoning in video generation. Grounded in developmental and social psychology, the benchmark covers thirty classic social cognition paradigms spanning seven core dimensions: mental-state inference, goal-directed action, joint attention, social coordination, prosocial behavior, social norms, and multi-agent strategy. To operationalize these paradigms, we build a fully training-free agent-based pipeline that distills the reasoning structure of each paradigm, synthesizes diverse video-ready scenarios, enforces conceptual neutrality and difficulty control through cue-based critique, and evaluates generated videos with a high-capacity VLM judge along five interpretable dimensions of social reasoning. Using this framework, we conduct the first large-scale evaluation of seven state-of-the-art video generation systems. Results show a clear gap between surface-level plausibility and deeper social reasoning, suggesting that current models remain limited in their ability to generate socially grounded behavior. https://github.com/Gloria2tt/SVBench-Evaluation