Reliability annotation for tabular QA reaches near-perfect accuracy with about 200 schema-stratified SFT examples, and GRPO adds measurable value only when SFT is undertrained.
Ilyas, and Christopher Ré
1 Pith paper cite this work, alongside 2 external citations. Polarity classification is still indexing.
1
Pith paper citing it
2
external citations · OpenAlex
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ReliableTableQA:How Much Supervision Does Reliability Annotation Need?
Reliability annotation for tabular QA reaches near-perfect accuracy with about 200 schema-stratified SFT examples, and GRPO adds measurable value only when SFT is undertrained.