FinRAG-12B: A Production-Validated Recipe for Grounded Question Answering in Banking
Researchers introduce FinRAG-12B, a 12-billion parameter language model designed for grounded question answering in the banking sector, trained on just 143 million tokens. The model surpasses GPT-4.1 in citation grounding, achieves a calibrated 12% refusal rate, and is deployed at over 40 financial institutions, where it improves query resolution by 7.1 percentage points. The system also delivers responses 3-5 times faster and at 20-50 times lower cost compared to GPT-4.1.
Why it matters: This work demonstrates a practical, data-efficient approach for building domain-specific LLMs that satisfy the accuracy, grounding, and compliance needs of regulated industries such as banking.
Full story at: arXiv Multiagent Systems ↗