FinRAG-QA benchmark dataset tackles automated financial statement analysis

LLMs match human referees on finance papers, but miss nuance in accounting

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

GPT-4o referee verdicts correlated 44% stronger with top-journal acceptances than human peer review, suggesting LLMs can assist but not replace accounting/finance journal review processes.

LLM sentiment measures diverge sharply across models on earnings transcripts

HQ arXiv: AI + Accounting arXiv · 25d ago · 1 min read

Study of 7 LLMs analyzing S&P 500 earnings calls finds textual measures (sentiment, uncertainty, risk) correlate only 0.52 across models, raising reliability concerns for accounting research using ...

Knowledge graph system makes equity analyst queries auditable and reproducible

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

OntoKG-EQ addresses the audit and reproducibility crisis in equity analysis by replacing ad-hoc spreadsheets with a provenance-grounded knowledge graph that links analyst queries to evidence, times...

Researchers audit LLM consistency on real venture-financing documents

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

Probity benchmark reveals LLMs give inconsistent answers on identical accounting queries 60+ times; researchers identify systematic defect where evidence is hidden from model's visible context window.

FinRank benchmark tests AI accuracy on SEC filing questions

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

New research introduces FinRank, a benchmark for evaluating AI systems on financial question answering over SEC filings, focusing on evidence provenance rather than answer correctness alone.