FiMI: A Domain-Specific Language Model for Indian Finance Ecosystem
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915795652575232 |
|---|---|
| author | Kathar, Aboli Kumar, Aman Kamath, Anusha Srujan, Araveeti Sharma, Ashish Bhushan, Chandra Sorate, Divya Kumar, Duddu Prasanth Acharya, Evan Sharma, Harsh Kadam, Hrithik Singla, Kanishk Doshi, Keyur Praveen, Kiran SK, Kolisetty Krishna Adhikary, Krishanu MPT, Lokesh Sonowal, Mayurdeep Shaikh, Nadeem Prakash, Navya Kothari, Nimit Kukreja, Nitin Devadiga, Prashant Paul, Rakesh Chauhan, Ratanjeet Pratap Kalani, Raunak Joshi, Raviraj MH, Shamanth Pandey, Shantanu Soni, Shubham Dixit, Siddharth Jopat, Smriti Patel, Sunil Singh, Suraj Paul, Suvradip Pilla, Tulasi Vaidya, Utkarsh Nambiar, Vineeth Kanvaty, Vishal Dedhia, Yatharth |
| author_facet | Kathar, Aboli Kumar, Aman Kamath, Anusha Srujan, Araveeti Sharma, Ashish Bhushan, Chandra Sorate, Divya Kumar, Duddu Prasanth Acharya, Evan Sharma, Harsh Kadam, Hrithik Singla, Kanishk Doshi, Keyur Praveen, Kiran SK, Kolisetty Krishna Adhikary, Krishanu MPT, Lokesh Sonowal, Mayurdeep Shaikh, Nadeem Prakash, Navya Kothari, Nimit Kukreja, Nitin Devadiga, Prashant Paul, Rakesh Chauhan, Ratanjeet Pratap Kalani, Raunak Joshi, Raviraj MH, Shamanth Pandey, Shantanu Soni, Shubham Dixit, Siddharth Jopat, Smriti Patel, Sunil Singh, Suraj Paul, Suvradip Pilla, Tulasi Vaidya, Utkarsh Nambiar, Vineeth Kanvaty, Vishal Dedhia, Yatharth |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05794 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FiMI: A Domain-Specific Language Model for Indian Finance Ecosystem Kathar, Aboli Kumar, Aman Kamath, Anusha Srujan, Araveeti Sharma, Ashish Bhushan, Chandra Sorate, Divya Kumar, Duddu Prasanth Acharya, Evan Sharma, Harsh Kadam, Hrithik Singla, Kanishk Doshi, Keyur Praveen, Kiran SK, Kolisetty Krishna Adhikary, Krishanu MPT, Lokesh Sonowal, Mayurdeep Shaikh, Nadeem Prakash, Navya Kothari, Nimit Kukreja, Nitin Devadiga, Prashant Paul, Rakesh Chauhan, Ratanjeet Pratap Kalani, Raunak Joshi, Raviraj MH, Shamanth Pandey, Shantanu Soni, Shubham Dixit, Siddharth Jopat, Smriti Patel, Sunil Singh, Suraj Paul, Suvradip Pilla, Tulasi Vaidya, Utkarsh Nambiar, Vineeth Kanvaty, Vishal Dedhia, Yatharth Artificial Intelligence Computational Engineering, Finance, and Science Computation and Language Machine Learning 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. |
| title | FiMI: A Domain-Specific Language Model for Indian Finance Ecosystem |
| topic | Artificial Intelligence Computational Engineering, Finance, and Science Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2602.05794 |