An ablation study on 252 datasets finds that adding table schemas to LLM prompts consistently degrades narrative quality of generated descriptions compared to titles alone.
Data reusers’ trust development,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DB 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Less Is More? When Dataset Context Hurts LLM-Generated Dataset Descriptions
An ablation study on 252 datasets finds that adding table schemas to LLM prompts consistently degrades narrative quality of generated descriptions compared to titles alone.