STAGE generates source-grounded text-to-JSON training data via spreadsheet validation, raising Qwen3-4B exact match from 31.37% to 74.27% on the 851-example STAGE-Eval benchmark.
arXiv preprint arXiv:2511.04473 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Source-Grounded Data Generation for Text-to-JSON Learning
STAGE generates source-grounded text-to-JSON training data via spreadsheet validation, raising Qwen3-4B exact match from 31.37% to 74.27% on the 851-example STAGE-Eval benchmark.