Researchers fine-tune DeepSeek-R1-8B with LoRA and NEFTune to improve financial named-entity recognition, enabling better extraction of structured data from unstructured reports and news for knowle...
ArXiv paper on Collaborative Human-Agent Protocol (CHAP) for managing multi-human, multi-agent systems in production—relevant to accounting firms deploying AI agents across audit, tax, and complian...
New multi-agent framework DuMate-DeepResearch addresses hallucination and verification challenges in deep research tasks through recursive search and rubric-grounded reasoning, with direct applicat...
New methodology LoRA-MINT enables auditing of training data membership in domain-adapted LLMs, addressing IP and data sensitivity concerns for accounting applications.
Academic paper introduces methods to trace and verify LLM agent decision-making through execution provenance, addressing audit and compliance needs for autonomous AI systems in high-stakes domains.
Agentic Redux, a new LLM agent architecture, uses typed lambda calculus to guarantee semantic correctness with append-only ledger auditability, demonstrated in healthcare billing compliance and sec...
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...
Academic paper proposes Violation Situation Pattern (VSP), a knowledge-graph approach that converts transient compliance violations into persistent audit objects with lifecycle tracking, review sta...
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 ...
Blue J and CPA.com survey shows tax practitioners moving beyond experimentation to embed AI as core workflow tool, signaling shift from pilot projects to firm-wide transformation.