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.
Integration patterns in the use of metadata for data sense-making during relevance evaluation: An interpretable deep learning-based prediction,
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.