Tree-of-Text guides LLMs through a three-stage tree process of planning operations on input tables, executing them on sub-tables, and merging short texts into full sports reports, outperforming baselines on ShuttleSet+, RotoWire-FG, and MLB while using 40% of the time and cost of Chain-of-Table.
InProceedings of the 2017 Conference on Empiri- cal Methods in Natural Language Processing, pages 2253–2263, Copenhagen, Denmark
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Tree-of-Text: A Tree-based Prompting Framework for Table-to-Text Generation in the Sports Domain
Tree-of-Text guides LLMs through a three-stage tree process of planning operations on input tables, executing them on sub-tables, and merging short texts into full sports reports, outperforming baselines on ShuttleSet+, RotoWire-FG, and MLB while using 40% of the time and cost of Chain-of-Table.