用基金披露数据构建专业理财顾问人格，提升AI建议的精准度。
Fund2Persona: A Framework for Building and Refining Financial Advisor Personas from Fund Disclosure Data
- 从真实基金披露数据生成顾问人格，通过三阶段循环优化
- 预测持仓变动准确率超通用基线，且评论更贴近基金经理解释
- 适合需要个性化投资建议的场景，如对话式理财或市场模拟
个性化金融建议需求日益增长，但现有基于大模型的顾问常缺乏一致性与专业性。简单的人格提示难以明确推理方式，易产生泛化建议。我们提出 Fund2Persona 框架，基于真实基金披露数据构建理财顾问人格，并通过「演员-评分器-修复器」循环进行迭代优化。实验表明，该框架在预测待测持仓变化和生成与基金经理解释一致的评论方面均优于通用基线。进一步评估显示，在市场情景生成任务中，人格检索可拓展合理投资视角；在多轮投资者-顾问对话中，匹配的人格能提供更具体、更有价值的建议。结果表明，真实基金数据可将管理人特有的投资专长注入大模型顾问，而非仅改变表面风格。
原文摘要 · Abstract (English)
Demand for personalized financial advice is growing, yet current LLM-based advisors often fail to provide consistent and specialized guidance.\ Simple persona prompts rarely specify how a financial advisor should reason and often drift toward generic recommendations. We propose Fund2Persona, a framework that builds financial-advisor personas from real-world fund disclosures and refines them through an actor--scorer--patcher loop. We test whether the resulting personas can predict held-out portfolio changes and produce commentary consistent with fund managers' own explanations. They outperform generic baselines on both tasks. We further study two downstream diagnostics: market-scenario generation, where persona retrieval broadens plausible investment views, and multi-turn investor--advisor conversations, where matched personas give more specific and useful advice than a generic advisor. These results suggest that real fund data can bring manager-specific investment expertise to LLM advisors rather than merely changing an LLM's surface style.
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。