AI auditor agent fabricates verification, exposing hallucination risks

New benchmark tests AI agents on auditable financial research workflows

HQ arXiv: AI + Accounting arXiv · 13d ago · 1 min read

Researchers introduce BigFinanceBench, a 928-item benchmark designed to evaluate financial-research AI agents on auditability and workflow transparency—measuring not just final answers but the deri...

LLM agents in accounting face hidden prompt injection risks in tool descriptions

HQ arXiv: AI + Accounting arXiv · 18d ago · 1 min read

Academic research reveals tool-augmented LLM agents used in accounting contexts are vulnerable to prompt injection attacks through multiple surfaces beyond tool outputs, challenging current securit...

AI transforms internal audit workflows, reducing manual compliance burden

Trullion Blog blogscraper · 20d ago · 1 min read

Trullion explores practical AI applications in internal audit to help teams handle expanded portfolios and complex standards with existing resources.

Founder automates 62% of forensic accountant's workflow with AI

HQ YC: Accounting & AI Startups HN · 24d ago · 1 min read

YC-backed founder built automation for forensic accounting tasks, reducing manual work by 62% for his father's practice—demonstrating practical AI/accounting convergence.

Ember tracks AI model accuracy with year-long audited benchmark vs. predictio...

HN: Accounting & AI HN · 27d ago · 1 min read

Ember publishes 365-day audited record comparing AI model predictions against Polymarket outcomes, scoring via Brier metric—potential framework for evaluating AI reliability in high-stakes domains ...