PrepBench is a benchmark showing that state-of-the-art LLMs still struggle with natural-language-driven data preparation involving disambiguation, code generation, and workflow translation.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
GRACE dynamically constructs and updates coresets for LLM training using representation diversity, gradient-based importance, and k-NN graph propagation to improve efficiency and performance.
BDIViz is a visual analytics system that uses an ensemble of matching algorithms plus LLM validation and interactive heatmaps to improve accuracy and reduce time in biomedical schema matching.
citing papers explorer
-
PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?
PrepBench is a benchmark showing that state-of-the-art LLMs still struggle with natural-language-driven data preparation involving disambiguation, code generation, and workflow translation.
-
GRACE: A Dynamic Coreset Selection Framework for Large Language Model Optimization
GRACE dynamically constructs and updates coresets for LLM training using representation diversity, gradient-based importance, and k-NN graph propagation to improve efficiency and performance.
-
BDIViz: An Interactive Visualization System for Biomedical Schema Matching with LLM-Powered Validation
BDIViz is a visual analytics system that uses an ensemble of matching algorithms plus LLM validation and interactive heatmaps to improve accuracy and reduce time in biomedical schema matching.