FiMI: A Domain-Specific Language Model for Indian Finance Ecosystem

Read full text
Authors: Aboli Kathar, Aman Kumar, Kamath, Anusha, Araveeti V Sai Srujan, Ashish Sharma, Chandra Bhushan, Divya Sorate, Duddu Prasanth Kumar, Evan Acharya, H. B. SHARMA, Hrithik Kadam, Kanishk Singla
+28 more Keyur Doshi, Kiran Praveen, Kolisetty Krishna SK, Krishanu Adhikary, Lokesh MPT, Mayurdeep Sonowal, Nadeem Shaikh, Prakash, Navya, Nimit Kothari, Kukreja, Nitin, Prashant Devadiga, Rakesh Paul, Ratanjeet Pratap Chauhan, Raunak Kalani, Joshi, Raviraj, Shamanth MH, Shantanu Pandey, Shubham Soni, Siddharth Dixit, Smriti Jopat, Sunil Patel, Suraj Singh, Suvradip Paul, Tulasi Pilla, Urmi Vaidya, Vineeth Nambiar, Vishal Kanvaty, Yatharth Dedhia
Cited by: 0

Abstract

We present FiMI (Finance Model for India), a domain-specialized financial language model developed by National Payments Corporation of India (NPCI) for Indian digital payment systems. We develop two model variants: FiMI Base and FiMI Instruct. FiMI adapts the Mistral Small 24B architecture through a multi-stage training pipeline, beginning with continuous pre-training on 68 Billion tokens of curated financial, multilingual (English, Hindi, Hinglish), and synthetic data. This is followed by instruction fine-tuning and domain-specific supervised fine-tuning focused on multi-turn, tool-driven conversations that model real-world workflows, such as transaction disputes and mandate lifecycle management. Evaluations reveal that FiMI Base achieves a 20\% improvement over the Mistral Small 24B Base model on finance reasoning benchmark, while FiMI Instruct outperforms the Mistral Small 24B Instruct model by 87\% on domain-specific tool-calling. Moreover, FiMI achieves these significant domain gains while maintaining comparable performance to models of similar size on general benchmarks.

Fields of Study & Subjects

Topic Modeling Natural Language Processing Techniques Speech and dialogue systems

Publication details

Journal / source
arXiv (Cornell University)
Publication date
5 February 2026
Document type
Preprint