Academic research identifies distribution shift and scale as failure modes in contamination detection methods for auditing LLM training data, raising questions about the reliability of current asse...
Researchers propose AuditFlow, a graph-grounded multi-agent AI system that automates financial audit verification by linking reported facts to taxonomy concepts and recomputing values against audit...
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...
Researchers propose a guardrail orchestration layer that consolidates PII redaction, content moderation, and format validation for high-stakes financial documents like audit summaries and dispute n...
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 tool-augmented LLM agents used in accounting contexts are vulnerable to prompt injection attacks through multiple surfaces beyond tool outputs, challenging current securit...
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.
Research paper introduces EvaluatorDPT, a system for production AI to handle uncertain cases through policy-governed abstention and real-time steering, addressing audit requirements in high-stakes ...
Academic paper introduces formal model distinguishing agentic technical debt from stochastic tax, offering accounting teams metrics to measure and simulate AI agent governance risks and operating c...
Academic paper presents hybrid formal logic + neural method to verify LLM outputs in high-stakes domains like accounting, addressing hallucinations and consistency risks.
arXiv paper introduces counterfactual actuarial runtime layer for AI agents with per-action risk pricing and pre-transaction underwriting, relevant to audit and compliance oversight of autonomous s...
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...
Researchers introduce Trajel, a dataset and evaluation framework for detecting hallucinations across intermediate steps in multi-agent LLM workflows—critical for auditing AI agents in industrial se...
Researchers propose Ontological Knowledge Blocks (OKBs), a programmable framework that automates AI governance verification and compliance auditing beyond static checklists, targeting transparency ...
Academic theory explores how agentic AI orchestrators create modular technical interfaces but preserve integrated accountability boundaries for outputs requiring evidence, review, or assignable res...
Capterra survey of 500 US accounting managers finds 89% see ROI from AI tools in chatbots, data entry, and fraud detection, yet 52% experienced recent data breaches and most lack clear AI data-hand...