Invoice processing
Invoices against purchase orders: does it match, is it a duplicate, discrepancy severity, disposition, urgency.
On typed-decisions, Jev leads with 0.756 mean accuracy against a 0.572 majority baseline.
typed-decisions
Every model is zero-shot except LAYA typed-decisions, which was fine-tuned on this suite.
| # | Model | Mean accuracy | Baseline | Beats baseline |
|---|---|---|---|---|
| 1 | JevTypeSafe | 0.756 | 0.572 | 5/5 |
| 2 | LAYA typed-decisionsConvai Innovations | 0.734 | 0.572 | 4/5 |
| 3 | Vonwfzyx | 0.412 | 0.572 | 1/5 |
| 4 | GLiClass large v3.0Knowledgator | 0.388 | 0.572 | 1/5 |
| 5 | GLiNER2 largeFastino | 0.332 | 0.572 | 1/5 |
| 6 | GLiNER 2.5 baseFastino | 0.326 | 0.572 | 0/5 |
| 7 | LAYA multilingualConvai Innovations | 0.310 | 0.572 | 0/5 |
| 8 | GLiClass multilang ultraKnowledgator | 0.298 | 0.572 | 0/5 |
| 9 | LAYAConvai Innovations | 0.274 | 0.572 | 0/5 |
The questions
- td_invoice_processing.discrepancy_severity · score · LAYA's public suiteHow material is any discrepancy between the invoice, the order and the delivery?None: everything reconciles. · Trivial: rounding or a cosmetic difference. · Moderate: a real difference worth confirming. · Material: a large or unexplained difference.
- td_invoice_processing.disposition · choice · LAYA's public suiteHow should this vendor invoice be dispositioned?approve · hold · manual_review · reject
- td_invoice_processing.duplicate · noul · LAYA's public suiteThis invoice appears to duplicate an invoice already submitted.
- td_invoice_processing.matches_order · noul · LAYA's public suiteThe invoice reconciles with the purchase order and the recorded delivery.false · true
- td_invoice_processing.urgency · score · LAYA's public suiteHow time-sensitive is processing this invoice?No time pressure; can wait indefinitely. · Routine; handle within the normal queue. · Elevated; should be handled within the same week. · Critical; requires action within the same day.
Frequently asked questions
What does invoice processing involve?
Invoices against purchase orders: does it match, is it a duplicate, discrepancy severity, disposition, urgency.
Which model is best at invoice processing?
Jev leads on typed-decisions at 0.756 mean accuracy over 5 questions.
Related
Support tickets: which team, is a refund requested, how frustrated, churn risk, urgency, does a human need to step in. The domain TypeSafe uses in its own docs.
Alerts and incident write-ups: severity, active exploitation, credential compromise, true positive, disposition, urgency.
Traces of an autonomous agent run: outcome, risk, urgency, what the observability system should do, whether a human should review it.