合成基于行为的推理链：面向个人理财LLM的数据生成框架
Synthesizing Behaviorally-Grounded Reasoning Chains: A Data-Generation Framework for Personal Finance LLMs
AI总结：
本文提出一个可复现的框架，通过整合财务背景与行为金融学研究构建监督数据，生成19k推理数据集微调Qwen-3-8B模型，使其在事实准确性和个性化等指标上媲美14-32B大模型，且成本降低80%。
摘要：
个性化财务建议需要考虑用户目标、约束、风险承受能力和司法管辖区。先前的LLM研究主要集中在为投资者和财务规划师提供支持系统。同时，近期许多研究通过产生高昂维护成本的智能体管道来考察更广泛的个人理财任务，包括预算、债务管理、退休和遗产规划，其获得的财务回报不足预期的25%。在本研究中，我们引入了一个新颖且可复现的框架，该框架将相关财务背景与行为金融学研究相结合，为端到端顾问构建监督数据。使用该框架，我们创建了一个包含19k样本的推理数据集，并在该数据集上对Qwen-3-8B模型进行了全面的微调。通过留出测试集和盲法LLM评审研究，我们证明通过精心的数据筛选和行为整合，我们的8B模型在事实准确性、流畅性和个性化指标上取得了与显著更大的基线（14-32B参数）相当的性能，同时产生的成本比这些更大的同类模型低80%。
英文摘要：
Personalized financial advice requires consideration of user goals, constraints, risk tolerance, and jurisdiction. Prior LLM work has focused on support systems for investors and financial planners. Simultaneously, numerous recent studies examine broader personal finance tasks, including budgeting, debt management, retirement, and estate planning, through agentic pipelines that incur high maintenance costs, yielding less than 25% of their expected financial returns. In this study, we introduce a novel and reproducible framework that integrates relevant financial context with behavioral finance studies to construct supervision data for end-to-end advisors. Using this framework, we create a 19k sample reasoning dataset and conduct a comprehensive fine-tuning of the Qwen-3-8B model on the dataset. Through a held-out test split and a blind LLM-jury study, we demonstrate that through careful data curation and behavioral integration, our 8B model achieves performance comparable to significantly larger baselines (14-32B parameters) across factual accuracy, fluency, and personalization metrics while incurring 80% lower costs than the larger counterparts.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
