Multilingual Conversational AI for Financial Assistance: Bridging Language Barriers in Indian FinTech

ACL ARR 2025 July Submission208 Authors

Abstract: India's linguistic diversity presents both opportunities and challenges for fintech platforms. While the country has 31 major languages and over 100 minor ones, only 10% of the population understands English, creating barriers to financial inclusion. We present a multilingual conversational Al system for a financial assistance use case that supports code-mixed languages like Hinglish, enabling natural interactions for India's diverse user base. Our system employs a multi-agent architecture with language classification, function management, and multilingual response generation. Through comparative analysis of multiple language models and real-world deployment, we demonstrate significant improvements in user engagement while maintaining low latency overhead (4-8%). This work contributes to bridging the language gap in digital financial services for emerging markets.

Paper Type: Long

Research Area: Multilingualism and Cross-Lingual NLP

Research Area Keywords: multilingual AI, conversational AI, fintech

Contribution Types: NLP engineering experiment

Languages Studied: English, Hindi, Marathi, Gujarati, code-mixed languages (Hinglish)

Reassignment Request Area Chair: This is not a resubmission

Reassignment Request Reviewers: This is not a resubmission

A1 Limitations Section: This paper has a limitations section.

A2 Potential Risks: N/A

B Use Or Create Scientific Artifacts: Yes

B1 Cite Creators Of Artifacts: N/A

B2 Discuss The License For Artifacts: N/A

B3 Artifact Use Consistent With Intended Use: No

B3 Elaboration: We did not use any prop artifacts/non open-source libraries.

B4 Data Contains Personally Identifying Info Or Offensive Content: N/A

B5 Documentation Of Artifacts: N/A

B6 Statistics For Data: N/A

C Computational Experiments: Yes

C1 Model Size And Budget: N/A

C2 Experimental Setup And Hyperparameters: N/A

C3 Descriptive Statistics: N/A

C4 Parameters For Packages: N/A

D Human Subjects Including Annotators: Yes

D1 Instructions Given To Participants: Yes

D1 Elaboration: Section 4.5 : The human reviewers involved in evaluating the performance of the system were the same people who helped develop the system for the sole purpose of internal evaluation. No external evaluators were involved.

D2 Recruitment And Payment: N/A

D3 Data Consent: N/A

D4 Ethics Review Board Approval: N/A

D5 Characteristics Of Annotators: N/A

E Ai Assistants In Research Or Writing: Yes

E1 Information About Use Of Ai Assistants: Yes

E1 Elaboration: Section 'Declaration on Generative AI' : We utilized Claude and ChatGPT to assist in the drafting process of this paper. These models were employed for their language generation capabilities, aiding in the articulation of concepts and refining the overall readability of the text. Their use was limited to support the writing process, with all research, analysis, and core intellectual contributions originating from the authors.

Author Submission Checklist: yes

Submission Number: 208