打造懂金融常识的对话机器人，让理财建议更专业可信。
Fin-Ally: Pioneering the Development of an Advanced, Commonsense-Embedded Conversational AI for Money Matters
- 构建多轮金融对话数据集Fin-Vault，支持复杂财务场景交互。
- 通过常识嵌入与直接偏好优化，生成更专业、自然的理财回复。
- 适合金融科技公司开发高信任度智能客服，提升用户体验。
金融科技的快速发展推动了智能顾问聊天机器人的广泛应用。然而，大模型的粗调常导致不专业或轻率的回应，如‘用这笔钱，你将改变世界’——虽事实正确但语境不当，削弱用户信任。现有研究多聚焦孤立模块，如推理增强或拟人化生成。为此，本文提出Fin-Solution 2.0，包含：1）构建1,417条标注的多轮金融对话数据集Fin-Vault；2）推出统一模型Fin-Ally，融合常识推理、礼貌性与拟人对话动态。Fin-Ally基于嵌入常识上下文的COMET-BART，并通过直接偏好优化（DPO）机制训练，实现与人类对齐的响应。该模型可超越基础账户管理，提供个性化预算、实时支出追踪与自动化财务规划。实验表明，融入常识上下文显著提升语言模型生成内容的专业性、准确性和语义精细度，为金融科技领域下一代AI解决方案奠定基础。数据与代码已开源：https://github.com/sarmistha-D/Fin-Ally
原文摘要 · Abstract (English)
The 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. Dataset and codes are available at: https://github.com/sarmistha-D/Fin-Ally
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。