Researcher proposes evaluation protocols grounded in acceptance-test-driven development to ensure LLMs meet deterministic institutional requirements for safety, auditability, and economic utility—a...
Researchers propose an interaction-native knowledge system for financial AI agents that retain user context, preferences, and market assumptions to reduce errors and improve auditability in trading...
Production study demonstrates HOPM framework for auditable, evidence-grounded document generation in marketplace disputes—bridging AI reliability with accounting/compliance audit trails.
Researchers address numerical hallucinations in LLM-powered financial Q&A systems via data-centric compilation, improving reliability for high-stakes accounting applications where accuracy is criti...
Academic research reveals that per-token LLM billing lacks auditability safeguards, enabling dishonest providers to overcharge—a critical issue for accounting firms using AI tools at scale.
FinVerBench evaluates 15 LLMs on numerical consistency checks in SEC 10-K filings, introducing error taxonomy across arithmetic, linkage, and magnitude categories to measure AI readiness for financ...
Research on HOPE-inspired nested learning with semantic caching cuts LLM hallucinations in multi-agent pipelines, critical for reliable accounting automation systems.
Academic paper presents hybrid formal logic + neural method to verify LLM outputs in high-stakes domains like accounting, addressing hallucinations and consistency risks.
New machine learning approach improves extraction and classification of numerical data from financial reports despite errors in manual XBRL labeling, advancing AI understanding of accounting docume...
Research proposes 'governance from metrics' approach treating LLM compliance as continuous runtime signal rather than binary audit verdict, addressing EU AI Act requirements for ongoing oversight a...
Brazilian forensic accountant demonstrates how to use Claude AI for expert witness reports while maintaining technical rigor and professional standards.
Podcast breaks down six concrete Claude use cases accounting firms are already implementing, including SOP generation from screen recordings and multi-entity financial consolidation.
KPMG and Anthropic partnership leverages Claude AI to develop a digital gateway combining frontier AI capabilities with accounting domain expertise, emphasizing security and trust.
Anthropic employee runs large-scale bookkeeping operation using Claude Cowork, demonstrating real-world LLM application in accounting workflow automation at enterprise scale.
Kepler develops novel double-entry evaluation framework combining code-based metrics and LLM assessment to grade accounting task quality, extracting most value from disagreements between evaluation...
Keeper Tax explains how self-employed individuals can deduct AI tool subscriptions (ChatGPT, Claude) as business expenses on Schedule C tax returns.
EY's 2025 Canada report on fraud in loyalty systems was 72% AI-generated with 16+ hallucinations, raising concerns about AI reliability in audit and fraud-detection work.
Snowflake explains how semantic layers—shared meaning of data—are essential for AI risk models and agents making autonomous decisions in financial services without understanding underlying data con...
Researchers identify principal-agent failures in LLMs used for regulated financial decisions, where models appear compliant while violating governance at the rationale level; propose five metrics t...