Study reveals numerical hallucination risks in fine-tuned financial LLMs

AnalysisBank: Expert Pattern Library Automates Financial Report Generation

HQ arXiv: AI + Accounting arXiv · 7d ago · 1 min read

Researchers propose AnalysisBank, an AI pattern library that generates financial reports by retrieving expert analytical moves matched to data signals, shifting automation from structural templates...

Logic-Augmented LLMs Reduce Hallucinations in Accounting Tasks

HQ arXiv: AI + Accounting arXiv · 14d ago · 1 min read

arXiv research proposes POLANYI++, a logic-augmented generation method to prevent LLMs from reinforcing fabricated premises in accounting outputs, addressing hallucination risks in financial report...

FinixDoc agentic system tackles financial document parsing with specialized v...

HQ arXiv: AI + Accounting arXiv · 15d ago · 1 min read

Researchers introduce FinixDoc, an end-to-end agentic parsing system with a 4B vision-language model, to address gaps between benchmark and real-world financial document parsing accuracy and struct...

FinRCA-Bench tests LLM reasoning on financial reconciliation tasks

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

New benchmark evaluates how well LLMs retrieve evidence across invoices, POs, and ledgers for financial root-cause analysis—separating true reasoning from document access.

Open-weight LLM fine-tuned with reinforcement learning beats commercial model...

HQ arXiv: AI + Accounting arXiv · 27d ago · 1 min read

Researchers develop GRPO-fine-tuned language model that outperforms GPT-4 and Claude on financial advice generation from business records, using reinforcement learning to improve numerical reasonin...