LLMs struggle with financial math; researchers propose data-centric fix for Q...

Financial LLM Agents Need Better Memory to Handle Market Complexity

HQ arXiv: AI + Accounting arXiv · 22h ago · 1 min read

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...

New benchmark tests LLMs on financial statement verification accuracy

HQ arXiv: AI + Accounting arXiv · 4d ago · 1 min read

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...

Researchers develop noise-robust AI for financial numerical entity tagging

HQ arXiv: AI + Accounting arXiv · 8d ago · 1 min read

New machine learning approach improves extraction and classification of numerical data from financial reports despite errors in manual XBRL labeling, advancing AI understanding of accounting docume...

Semantic layers cut LLM hallucinations in analytical databases by 34%

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

Research benchmarks Claude Opus, Sonnet, and GPT-5.4 on 100 accounting queries, showing semantic context layers reduce hallucination rates and improve answer accuracy for LLM-powered data analytics.

New framework improves LLM financial reasoning without expensive fine-tuning

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

ASDA framework outperforms existing methods (GEPA, ACE) on financial reasoning benchmarks, enabling cost-effective LLM adaptation for specialized financial tasks without model-locking.