Same-Number Citation Swaps: Stress-Testing Jev as a Financial Evidence Judge
Factual evidence
What the source reports
Researchers benchmarked Jev, a source verifier for LLMs, to detect when financial calculations cite wrong identical numbers.
Inspect the evidence
- Inclusion basis
- Enterprise AI
- Publisher and source type
- arXiv cs.CL — Computation and Language · RESEARCH
- Published by source
- 7 October 2026
- Collected by OneBench
- 8 Oct 2026, 03:01 UK
Stored source excerpt
arXiv:2610.08675v1 Announce Type: new Abstract: Financial reports repeat values across periods, metrics and accounting lines, allowing an LLM-generated calculation to be numerically correct while citing…
Short excerpt from the collected text, not the full source. Use the source link to read it in context.
The factual summary is a OneBench synthesis, not a quotation or independent verification. Collection time is not publication time. Open the source for its full context; related reporting can share the same underlying announcement.
OneBench interpretation
Institutional assessment
So what
Numerically correct financial outputs from language models frequently cite incorrect source lines, creating hidden audit and validation risks.
Do what
Review output verification controls for financial document processing models with your model risk management team.