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.
Text-to-pipeline: Bridging natural language and data preparation pipelines
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
PlanCompiler uses a typed node registry, static validation, and deterministic compilation to reach 278/300 successes on structured LLM pipeline benchmarks, outperforming GPT-4.1 and Claude Sonnet baselines at lower cost.
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.
-
PlanCompiler: A Deterministic Compilation Architecture for Structured Multi-Step LLM Pipelines
PlanCompiler uses a typed node registry, static validation, and deterministic compilation to reach 278/300 successes on structured LLM pipeline benchmarks, outperforming GPT-4.1 and Claude Sonnet baselines at lower cost.