@inproceedings{chua-etal-2025-banking,
title = "Banking Done Right: Redefining Retail Banking with Language-Centric {AI}",
author = "Chua, Xin Jie and
Tan, Jeraelyn Ming Li and
Tan, Jia Xuan and
Poh, Soon Chang and
Goh, Yi Xian and
Choong, Debbie Hui Tian and
Mun, Foong Chee and
Yang, Sze Jue and
Chan, Chee Seng",
editor = "Potdar, Saloni and
Rojas-Barahona, Lina and
Montella, Sebastien",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2025",
address = "Suzhou (China)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-industry.45/",
pages = "646--658",
ISBN = "979-8-89176-333-3",
abstract = "This paper presents Ryt AI, an LLM-native agentic framework that powers Ryt Bank to enable customers to execute core financial transactions through natural language conversation. This represents the first global regulator-approved deployment worldwide where conversational AI functions as the primary banking interface, in contrast to prior assistants that have been limited to advisory or support roles. Built entirely in-house, Ryt AI is powered by ILMU, a closed-source LLM developed internally, and replaces rigid multi-screen workflows with a single dialogue orchestrated by four LLM-powered agents (Guardrails, Intent, Payment, and FAQ). Each agent attaches a task-specific LoRA adapter to ILMU, which is hosted within the bank{'}s infrastructure to ensure consistent behavior with minimal overhead. Deterministic guardrails, human-in-the-loop confirmation, and a stateless audit architecture provide defense-in-depth for security and compliance. The result is Banking Done Right: demonstrating that regulator-approved natural-language interfaces can reliably support core financial operations under strict governance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chua-etal-2025-banking">
<titleInfo>
<title>Banking Done Right: Redefining Retail Banking with Language-Centric AI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="given">Jie</namePart>
<namePart type="family">Chua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeraelyn</namePart>
<namePart type="given">Ming</namePart>
<namePart type="given">Li</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jia</namePart>
<namePart type="given">Xuan</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soon</namePart>
<namePart type="given">Chang</namePart>
<namePart type="family">Poh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="given">Xian</namePart>
<namePart type="family">Goh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debbie</namePart>
<namePart type="given">Hui</namePart>
<namePart type="given">Tian</namePart>
<namePart type="family">Choong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Foong</namePart>
<namePart type="given">Chee</namePart>
<namePart type="family">Mun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sze</namePart>
<namePart type="given">Jue</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chee</namePart>
<namePart type="given">Seng</namePart>
<namePart type="family">Chan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saloni</namePart>
<namePart type="family">Potdar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lina</namePart>
<namePart type="family">Rojas-Barahona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastien</namePart>
<namePart type="family">Montella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou (China)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-333-3</identifier>
</relatedItem>
<abstract>This paper presents Ryt AI, an LLM-native agentic framework that powers Ryt Bank to enable customers to execute core financial transactions through natural language conversation. This represents the first global regulator-approved deployment worldwide where conversational AI functions as the primary banking interface, in contrast to prior assistants that have been limited to advisory or support roles. Built entirely in-house, Ryt AI is powered by ILMU, a closed-source LLM developed internally, and replaces rigid multi-screen workflows with a single dialogue orchestrated by four LLM-powered agents (Guardrails, Intent, Payment, and FAQ). Each agent attaches a task-specific LoRA adapter to ILMU, which is hosted within the bank’s infrastructure to ensure consistent behavior with minimal overhead. Deterministic guardrails, human-in-the-loop confirmation, and a stateless audit architecture provide defense-in-depth for security and compliance. The result is Banking Done Right: demonstrating that regulator-approved natural-language interfaces can reliably support core financial operations under strict governance.</abstract>
<identifier type="citekey">chua-etal-2025-banking</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-industry.45/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>646</start>
<end>658</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Banking Done Right: Redefining Retail Banking with Language-Centric AI
%A Chua, Xin Jie
%A Tan, Jeraelyn Ming Li
%A Tan, Jia Xuan
%A Poh, Soon Chang
%A Goh, Yi Xian
%A Choong, Debbie Hui Tian
%A Mun, Foong Chee
%A Yang, Sze Jue
%A Chan, Chee Seng
%Y Potdar, Saloni
%Y Rojas-Barahona, Lina
%Y Montella, Sebastien
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou (China)
%@ 979-8-89176-333-3
%F chua-etal-2025-banking
%X This paper presents Ryt AI, an LLM-native agentic framework that powers Ryt Bank to enable customers to execute core financial transactions through natural language conversation. This represents the first global regulator-approved deployment worldwide where conversational AI functions as the primary banking interface, in contrast to prior assistants that have been limited to advisory or support roles. Built entirely in-house, Ryt AI is powered by ILMU, a closed-source LLM developed internally, and replaces rigid multi-screen workflows with a single dialogue orchestrated by four LLM-powered agents (Guardrails, Intent, Payment, and FAQ). Each agent attaches a task-specific LoRA adapter to ILMU, which is hosted within the bank’s infrastructure to ensure consistent behavior with minimal overhead. Deterministic guardrails, human-in-the-loop confirmation, and a stateless audit architecture provide defense-in-depth for security and compliance. The result is Banking Done Right: demonstrating that regulator-approved natural-language interfaces can reliably support core financial operations under strict governance.
%U https://aclanthology.org/2025.emnlp-industry.45/
%P 646-658
Markdown (Informal)
[Banking Done Right: Redefining Retail Banking with Language-Centric AI](https://aclanthology.org/2025.emnlp-industry.45/) (Chua et al., EMNLP 2025)
ACL
- Xin Jie Chua, Jeraelyn Ming Li Tan, Jia Xuan Tan, Soon Chang Poh, Yi Xian Goh, Debbie Hui Tian Choong, Foong Chee Mun, Sze Jue Yang, and Chee Seng Chan. 2025. Banking Done Right: Redefining Retail Banking with Language-Centric AI. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 646–658, Suzhou (China). Association for Computational Linguistics.