用大模型+棒球数据智能生成有叙事感的精彩集锦
DIAMOND: An LLM-Driven Agent for Context-Aware Baseball Highlight Summarization
- 结合棒球统计指标与大模型推理，兼顾量化重要性与故事性
- 在韩棒球联赛数据上F1得分从42.9%提升至84.8%
- 适合需要深度语境理解的体育赛事内容生成场景
传统方法如基于胜率增加值（WPA）的排序或计算机视觉事件检测，虽能识别得分动作，却常忽略战略深度、局势变化和剧情推进。人工编辑仍是金标准，但成本高且难扩展。我们提出DIAMOND，一种基于大模型的上下文感知棒球精彩集锦生成代理，融合结构化体育分析与自然语言推理。DIAMOND利用进垒期望、WPA和杠杆指数等棒球统计特征量化比赛关键时刻，同时通过大模型模块根据上下文叙事价值增强选段判断。该混合方法兼顾定量严谨性与定性丰富性，突破纯统计或视觉系统局限。在五场韩国棒球联盟比赛中评估，其F1得分由仅用WPA的42.9%提升至84.8%，优于商业及统计基线。尽管规模有限，结果凸显了模块化、可解释的代理框架在体育事件级摘要中的潜力。
原文摘要 · Abstract (English)
Traditional approaches -- such as Win Probability Added (WPA)-based ranking or computer vision-driven event detection -- can identify scoring plays but often miss strategic depth, momentum shifts, and storyline progression. Manual curation remains the gold standard but is resource-intensive and not scalable. We introduce DIAMOND, an LLM-driven agent for context-aware baseball highlight summarization that integrates structured sports analytics with natural language reasoning. DIAMOND leverages sabermetric features -- Win Expectancy, WPA, and Leverage Index -- to quantify play importance, while an LLM module enhances selection based on contextual narrative value. This hybrid approach ensures both quantitative rigor and qualitative richness, surpassing the limitations of purely statistical or vision-based systems. Evaluated on five diverse Korean Baseball Organization League games, DIAMOND improves F1-score from 42.9% (WPA-only) to 84.8%, outperforming both commercial and statistical baselines. Though limited in scale, our results highlight the potential of modular, interpretable agent-based frameworks for event-level summarization in sports and beyond.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。