ENTLORE benchmark evaluates how well AI systems recover implicit organizational relationships across enterprise documents—a key challenge for automated financial analysis and reporting.
Research validates how AI agent frameworks use text-embedding cosine similarity thresholds as quality gates for deduplication and semantic caching, finding measurement gaps between semantic meaning...
Researchers propose SAGE-Fin, a structured authority-handoff contract system that prevents AI financial agents from executing unauthorized transactions by controlling proposed effects at runtime ra...
Researchers argue AI model evaluation for accounting must measure verification effort, not just correctness—identifying a new failure mode where auditors miss errors within budget constraints.
Updated Financial Touchstone benchmark with 2,967 Q&A pairs from 495 annual reports tests 20 open-weight and proprietary models; Chinese AI labs' models show improved financial text comprehension b...
New Doc2DB-Bench research evaluates AI systems at converting unstructured financial and operational documents into queryable relational databases with integrity constraints—critical for compliance,...
IntelliAudit uses retrieval-grounded multi-agent LLMs to automate IT audit evidence evaluation by synthesizing heterogeneous organizational data across policies and records—addressing the semantic ...
New research introduces FinRank, a benchmark for evaluating AI systems on financial question answering over SEC filings, focusing on evidence provenance rather than answer correctness alone.
Researchers introduce A²E (Agent Auditing Engine), an end-to-end evaluation framework for assessing LLM agent capabilities across domains, addressing the gap in systematic auditing of complex agent...
Academic researchers present A²E, a systematic evaluation framework for auditing LLM-based agents, addressing gaps in capability testing critical for enterprise AI deployments in regulated domains ...
An AI agent is automating client follow-up and collections work for accounting firms, handling the high-friction tasks that tax and bookkeeping professionals avoid.
Otto Capture launches receipt automation tool aimed at small accounting practices, addressing manual expense capture workflows in bookkeeping.
YC-backed SecondState automates financial data prep for audits and diligence using AI agents to build data pipelines with human approval gates, targeting the pre-analytics layer competitors skip.
YC-backed Celerp launches local-first accounting software with modular architecture enabling users to build custom modules via AI coding tools without forking the codebase.
OpenAI's CFO Sarah Friar reveals lessons from deploying AI across forecasting, controls, and ROI measurement in finance operations, offering practical insights for enterprise adoption.
LogicGate argues third-party risk management can't rely on prompt-based AI tools; DORA and EU AI Act require auditable, purpose-built agents with documented approvals and compliance evidence.
Hacker News discussion raises questions about whether AI systems' audit trails meet regulatory standards during compliance audits, highlighting a gap in AI transparency for accounting oversight.
CLA, a top-10 US accounting firm, is investing in a three-year build with Digits to train a proprietary AI model on its client accounting practice, capturing transaction judgments to create reusabl...
Botkeeper shares a practical framework for accelerating month-end close cycles by up to 80% through automation and process optimization, targeting accounting teams managing complex close timelines.
BlackLine warns CFOs that generic AI models create regulatory and operational risks in finance, presenting a strategic choice between competitive advantage and compliance vulnerability.