New STAGE pipeline boosts text-to-JSON accuracy with LLM-generated data

Researchers have developed STAGE, a novel pipeline for generating training data for text-to-JSON conversion. This method uses large language models to synthesize reports and JSON schemas, with ground-truth values validated against underlying spreadsheets. STAGE-Eval, a new benchmark dataset, demonstrates STAGE's effectiveness, significantly improving the performance of the Qwen3-4B model on exact match and value accuracy tasks. AI

IMPACT Enhances structured data extraction capabilities, potentially improving efficiency in industries reliant on document analysis.

RANK_REASON The cluster contains a research paper detailing a new method and benchmark for text-to-JSON learning. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• alphaXiv
• arXiv
• CatalyzeX
• DagsHub
• Gotit.pub
• Hugging Face
• Qwen3-4B
• ScienceCast
• STAGE-Eval

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →