Research: LLM audit framework traces training data to model outputs

DuMate-DeepResearch system tackles auditable multi-agent reasoning for comple...

HQ arXiv: AI + Accounting arXiv · 17d ago · 1 min read

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...

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

HQ arXiv: AI + Accounting arXiv · 17d 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.

Study exposes blind spots in LLM benchmark contamination detection

HQ arXiv: AI + Accounting arXiv · 20d ago · 1 min read

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

HQ arXiv: AI + Accounting arXiv · 25d 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 benchmark tests LLMs on financial statement verification accuracy