Researchers propose method to correct noisy labels in automated accounting cl...

Framework improves LLM confidence calibration for reliable deployment

HQ arXiv: AI + Accounting arXiv · 4d ago · 1 min read

RADAR framework addresses confidence scoring in LLMs through repair, adoption, and error auditing—enabling better quality control for mission-critical accounting tasks.

Study reveals LLM judges fail to reliably assess AI performance at occupation...

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

Researchers audit 33 LLM judge configurations against 45,796 worker ratings, finding that high pair accuracy doesn't guarantee agreement on acceptance rates—critical for deploying AI in workplace t...

LLMs show promise at catching fraudulent backtests with new calibration bench...

HQ arXiv: AI + Accounting arXiv · 26d ago · 1 min read

Researchers introduce a 96-item paired benchmark to test whether LLMs can reliably audit financial backtests for methodology flaws while avoiding false positives on legitimate strategies.

LLMs fail as automated auditors when document contamination scales, study finds

HQ arXiv: AI + Accounting arXiv · 1mo ago · 1 min read

Research testing Google Gemini 3.0 Pro on 450 planted document errors reveals LLMs suffer batch-size degradation and confident hallucination—critical vulnerabilities for automated audit applications.

SerenAI system generates verifiable audit predictions via state-transition mo...