Study exposes blind spots in LLM benchmark contamination detection

Researchers develop LoRA-MINT to audit training data in fine-tuned LLMs

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

New methodology LoRA-MINT enables auditing of training data membership in domain-adapted LLMs, addressing IP and data sensitivity concerns for accounting applications.

Researchers expose LLM token billing auditing gaps as providers hide pricing ...

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

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.

New Training Method Improves LLM Reliability for Accounting Compliance Tasks

HQ arXiv: AI + Accounting arXiv · 2mo ago · 1 min read

Researchers propose DPA-GRPO, a paired-action training method to make LLMs more reliable for structured accounting workflows like form filling and compliance checking by ensuring outputs are locall...

Retrieval-Augmented Reasoning Improves LLM Performance on Indian Chartered Ac...

HQ arXiv: AI + Accounting arXiv · 2mo ago · 1 min read

Research introduces CA-ThinkFlow, an LLM framework designed to handle jurisdiction-specific chartered accountancy tasks including multi-step numerical reasoning and regulatory compliance without re...

AI-Generated Argument Graphs Enable Audit-Ready Compliance Documentation

HQ arXiv: AI + Accounting arXiv · 3mo ago · 1 min read

Researcher proposes using generative AI to automatically construct formal, evidence-linked argument graphs for regulatory compliance and certification audits, addressing traceability and accountabi...