We propose a rubric-guided, pseudo-labeled, and prompt-driven zero-shot video summarization framework that bridges large language models with structured semantic reasoning. A small subset of human annotations is converted into high-confidence pseudo labels and organized into dataset-adaptive rubrics defining clear evaluation dimensions such as thematic relevance, action detail, and narrative progression. During inference, boundary scenes, including the opening and closing segments, are scored independently based on their own descriptions, while intermediate scenes incorporate concise summaries of adjacent segments to assess narrative continuity and redundancy. This design enables the language model to balance local salience with global coherence without any parameter tuning. Across three benchmarks, the proposed method achieves stable and competitive results, with F1 scores of 57.58 on SumMe, 63.05 on TVSum, and 53.79 on QFVS, surpassing zero-shot baselines by +0.85, +0.84, and +0.37, respectively. These outcomes demonstrate that rubric-guided pseudo labeling combined with contextual prompting effectively stabilizes LLM-based scoring and establishes a general, interpretable, and training-free paradigm for both generic and query-focused video summarization.

翻译：我们提出了一种基于评分标准引导、伪标签驱动及提示驱动的零样本视频摘要框架，该框架将大语言模型与结构化语义推理相结合。少量人工标注被转化为高置信度的伪标签，并组织成适应数据集的评分标准，这些标准明确定义了如主题相关性、动作细节和叙事推进等评估维度。在推理过程中，边界场景（包括开头和结尾片段）根据其自身描述独立评分，而中间场景则结合相邻片段的简洁摘要以评估叙事连续性和冗余度。该设计使语言模型能够在无需参数调优的情况下平衡局部显著性与全局连贯性。在三个基准测试中，所提方法取得了稳定且具有竞争力的结果：在SumMe上F1分数为57.58，在TVSum上为63.05，在QFVS上为53.79，分别超越零样本基线+0.85、+0.84和+0.37。这些结果表明，评分标准引导的伪标签与上下文提示相结合，能有效稳定基于LLM的评分过程，并为通用视频摘要和查询聚焦视频摘要建立了一种通用、可解释且无需训练的范式。