Stanford releases open-source SEC filings dataset for LLM training

DeepSeek-R1 Model Trained for Financial Entity Recognition in Reports

HQ arXiv: AI + Accounting arXiv · 9d ago · 1 min read

Researchers fine-tune DeepSeek-R1-8B with LoRA and NEFTune to improve financial named-entity recognition, enabling better extraction of structured data from unstructured reports and news for knowle...

Financial LLM Agents Need Better Memory to Handle Market Complexity

HQ arXiv: AI + Accounting arXiv · 17d 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...

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

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

Researchers address numerical hallucinations in LLM-powered financial Q&A systems via data-centric compilation, improving reliability for high-stakes accounting applications where accuracy is criti...

New benchmark tests LLMs on financial statement verification accuracy

HQ arXiv: AI + Accounting arXiv · 21d 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 propose neuro-symbolic verification to catch LLM hallucinations i...

arXiv: AI + Accounting arXiv · 23d ago · 1 min read

Academic paper presents hybrid formal logic + neural method to verify LLM outputs in high-stakes domains like accounting, addressing hallucinations and consistency risks.