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

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chiang, Shang-Hsuan, Yang, Tsan-Tsung, Yen, An-Zi, Peng, Wen-Chih
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914516574404608
author Chiang, Shang-Hsuan
Yang, Tsan-Tsung
Yen, An-Zi
Peng, Wen-Chih
author_facet Chiang, Shang-Hsuan
Yang, Tsan-Tsung
Yen, An-Zi
Peng, Wen-Chih
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_26501
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Tree-of-Text: A Tree-based Prompting Framework for Table-to-Text Generation in the Sports Domain
Chiang, Shang-Hsuan
Yang, Tsan-Tsung
Yen, An-Zi
Peng, Wen-Chih
Computation and Language
Artificial Intelligence
Human-Computer Interaction
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.
title Tree-of-Text: A Tree-based Prompting Framework for Table-to-Text Generation in the Sports Domain
topic Computation and Language
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2604.26501