#double-entry

Double-Entry

Double-entry bookkeeping principles and their application in AI-assisted accounting

LLMs Score 2.3% on Beancount DSL Generation: The LLMFinLiteracy Benchmark

LLMFinLiteracy finds five ~7B models write correct Beancount transactions just 2.3% of the time, failing on accounting reasoning rather than syntax.

Mike Thrift

AuditCopilot cuts journal entry fraud false positives from 942 to 12, but ablation shows the LLM mainly synthesizes Isolation Forest scores.

Mike Thrift