Fin-Ally: Pioneering the Development of an Advanced, Commonsense-Embedded Conversational AI for Money Matters

Simple item page
dc.contributor.authorDas, Sarmistha
dc.contributor.authorMathur, Priya
dc.contributor.authorSharma, Ishani
dc.contributor.authorSaha, Sriparna
dc.contributor.authorPasupa, Kitsuchart
dc.contributor.authorMaurya, Alka
dc.date.accessioned2026-08-06T10:52:27Z
dc.date.available2026-08-06T10:52:27Z
dc.date.issued2025-10-21
dc.description.abstractThe exponential technological breakthrough of the FinTech industry has significantly enhanced user engagement through sophisticated advisory chatbots. However, large-scale fine-tuning of LLMs can occasionally yield unprofessional or flippant remarks, such as 'With that money, you're going to change the world,' which, though factually correct, can be contextually inappropriate and erode user trust. The scarcity of domain-specific datasets has led previous studies to focus on isolated components, such as reasoning-aware frameworks or the enhancement of human-like response generation. To address this research gap, we present Fin-Solution 2.O, an advanced solution that 1) introduces the multi-turn financial conversational dataset, Fin-Vault, and 2) incorporates a unified model, Fin-Ally, which integrates commonsense reasoning, politeness, and human-like conversational dynamics. Fin-Ally is powered by COMET-BART-embedded commonsense context and optimized with a Direct Preference Optimization (DPO) mechanism to generate human-aligned responses. The novel Fin-Vault dataset, consisting of 1,417 annotated multi-turn dialogues, enables Fin-Ally to extend beyond basic account management to provide personalized budgeting, real-time expense tracking, and automated financial planning. Our comprehensive results demonstrate that incorporating commonsense context enables language models to generate more refined, textually precise, and professionally grounded financial guidance, positioning this approach as a next-generation AI solution for the FinTech sector.
dc.identifier.citationFrontiers in Artificial Intelligence and Applications, 413, 4370-4377, 2025
dc.identifier.doi10.3233/FAIA251334
dc.identifier.issn09226389
dc.identifier.other2-s2.0-105024493684
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/17308
dc.sourceFrontiers in Artificial Intelligence and Applications
dc.titleFin-Ally: Pioneering the Development of an Advanced, Commonsense-Embedded Conversational AI for Money Matters
dc.typeConference Paper

Files

Collections

Research