用树状结构引导大模型生成体育比赛报告，提升准确率与效率。
Tree-of-Text: A Tree-based Prompting Framework for Table-to-Text Generation in the Sports Domain
- 构建三阶段树形提示框架，分步解析表格数据并生成内容。
- 在多个数据集上超越现有方法，尤其在RotoWire-FG和MLB上表现优异。
- 只需链式表法约40%的耗时与成本，适合快速部署的体育文本生成。
从结构化表格生成体育赛事报告是一项复杂任务，要求精确的数据理解与流畅的叙事能力。传统模型方法依赖大规模标注数据，而基于大语言模型（LLMs）的提示方法常因表格理解不足导致幻觉。为此，我们提出Tree-of-Text，一种树状结构提示框架，引导LLM经历三个阶段：(1) 内容规划，从输入表格中选择相关操作与参数；(2) 操作执行，将大表格拆分为可管理的子表；(3) 内容生成，将短文本合并并重写为连贯报告。实验表明，该方法在ShuttleSet+上优于现有方法，在RotoWire-FG上于RG和CO指标领先，在MLB上于CS和CO指标突出，且仅需Chain-of-Table约40%的时间与成本。结果验证了Tree-of-Text的有效性与高效性，为体育领域提示式表格到文本生成提供了新方向。
原文摘要 · Abstract (English)
Generating sports game reports from structured tables is a complex table-to-text task that demands both precise data interpretation and fluent narrative generation. Traditional model-based approaches require large, annotated datasets, while prompt-based methods using large language models (LLMs) often struggle with hallucination due to weak table comprehension. To overcome these challenges, we propose Tree-of-Text, a tree-structured prompting framework that guides LLMs through a three-stage generation process: (1) Content Planning, where relevant operations and arguments are selected from the input tables; (2) Operation Execution, which breaks down large tables into manageable sub-tables; and (3) Content Generation, where short textual outputs are merged and rewritten into a cohesive report. Experiments show that our method outperforms existing methods on ShuttleSet+, leads in RG and CO metrics on RotoWire-FG, and excels in CS and CO on MLB with roughly 40% of the time and cost of Chain-of-Table. These results demonstrate the effectiveness and efficiency of Tree-of-Text and suggest a promising direction for prompt-based table-to-text generation in the sports domain.
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。