Research paper

FinRAG-12B: A Production-Validated Recipe for Grounded Question Answering in Banking

Published by Association for Computational LinguisticsJul 2026PDF

Review a banking deployment that grounds answers in retrieved material and evaluates the resulting behaviour.

FinRAG-12B: A Production-Validated Recipe for Grounded Question Answering in Banking cover

Resource access

Get the full resource

Enter your business details to read the full resource.

First nameLast nameWork emailCompanyJob titleCountry or region

Denys Katerenchuk, Pablo Duboue, Keelan Evanini. FinRAG-12B: A Production-Validated Recipe for Grounded Question Answering in Banking. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track). © 2026 Association for Computational Linguistics. CC BY 4.0. 10.18653/v1/2026.acl-industry.92. Original PDF, unmodified.

CC BY 4.0

FinRAG-12B: A Production-Validated Recipe for Grounded Question Answering in Banking

Related research.

Learning Selective LLM Autonomy from Copilot Feedback in Enterprise Customer Support Workflows

ECom-Bench: Can LLM Agent Resolve Real-World E-commerce Customer Support Issues?

Retrieval Enhancements for RAG: Insights from a Deployed Customer Support Chatbot