Valid Per-Field Selective Risk Control for Document Extraction: Three Failure Modes, a Validity Ladder, and When Conditioning Pays
arXiv:2608.14639v1 Announce Type: new Abstract: Per-field accept/review with selective risk at most alpha -- accept a field only if the error rate among accepted fields is controlled -- is the trust contract document-extraction systems need, and the natural procedure silently violates it on real documents. On 13,859 genuine claude-sonnet-5 fields from 800 CORD receipts (49.0% correct) we diagnose three failure modes: document clustering (design effect 1.84-2.45), score-refit leakage (coverage 0....
arXiv cs.LG
·Bhaskar Gurram
·
// relacionados
Leia também
Blog
Flight attendants freaked out that Google is buying tons of Spirit employee data
Blog
Anthropic says any lab can now let a language model agent run the whole protein design stack
Blog
Forward Pass Domain Adaptation (Without Cross-Layer Backpropagation)
Blog