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.
| Comments: | Accepted by ACL SRW 2025: Long Paper (Oral) |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2604.26501 [cs.CL] |
| (or arXiv:2604.26501v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2604.26501 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Shang-Hsuan Chiang [view email]
[v1]
Wed, 29 Apr 2026 10:05:18 UTC (466 KB)