FinGREAT: Evaluating LLMs on Financial Graph-guided Retrieval And Typing
Factual evidence
What the source reports
Researchers introduced FinGREAT, a benchmark evaluating open-weight LLMs on schema-guided evidence discovery in double-entry accounting disclosures.
Inspect the evidence
- Inclusion basis
- Enterprise AI
- Publisher and source type
- arXiv cs.LG — Machine Learning · RESEARCH
- Published by source
- 15 October 2026
- Collected by OneBench
- 16 Oct 2026, 03:02 UK
Stored source excerpt
arXiv:2610.19240v1 Announce Type: new Abstract: Financial disclosures express the underlying relationships of double-entry accounting through unstructured text. While financial LLM benchmarks predominantly emphasize question answering…
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
Automating structured evidence discovery from double-entry accounting disclosures could streamline financial audit, compliance, and ledger reconciliation pipelines.
Do what
Review the benchmark methodology with the data architecture team to evaluate open-weight LLM capability for financial extraction tasks.