Tree-of-Text: A Tree-based Prompting Framework for Table-to-Text Generation in the Sports Domain

TL;DR

Tree-of-Text is a novel tree-structured prompting framework that enhances large language models' ability to generate accurate and fluent sports game reports from structured tables, improving performance and efficiency.

Contribution

The paper introduces Tree-of-Text, a three-stage prompting framework that guides LLMs in table-to-text generation, addressing hallucination and data comprehension issues.

Findings

Outperforms existing methods on ShuttleSet+

Leads in RG and CO metrics on RotoWire-FG

Achieves roughly 40% of the time and cost of Chain-of-Table

Abstract

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.