Skip to content

Fund2Persona: A Framework for Building and Refining Financial Advisor Personas from Fund Disclosure Data

Jun 2026 · arXiv.org · Vol abs/2606.29793 · 0 citations · 28 references
Computer Science Economics

TL;DR

Fund2Persona, a framework that builds financial-advisor personas from real-world fund disclosures and refines them through an actor-scorer-patcher loop, is proposed, suggesting that real fund data can bring manager-specific investment expertise to LLM advisors rather than merely changing an LLM's surface style.

Abstract

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.

View source

Similar papers

Preprint Sep 2026

InvestorNerd: An Investment and Financial Insights System Based on User Profiles

InvestorNerd is a web-based platform (investornerd.org) designed to educate and democratize financial understanding by providing accessible, AI-powered investment and personal finance insights tailored to potential user profiles. The system addresses a key challenge in helping everyday individuals, especially those wit...

J. Castillo, R. Gautam, Xin-Yuan Wang et al. · 0 citations
Preprint Aug 2026

GRPO for Financial Advice Generation: Outperforming Commercial LLMs under CATE Evaluation

It is demonstrated that GRPO with a finance-grounded reward signal can produce substantially more useful business recommendations than commercial LLMs, and that a judge-independent causal audit is a valuable complement to, rather than a confirmation of, LLM-as-a-judge assessment in financial NLP.

Ofir Ben Shoham, Shrutendra Harsola, Vignesh T. Subrahmaniam et al. · 0 citations
Sep 2026

Master Modeler: Learning Institutional Portfolio Construction with Large Language Models

Investment institutions exert substantial influence on asset prices, liquidity, and market stability, making the ability to forecast their portfolio adjustments both academically and practically important. We study modeling investment institutions by fine-tuning large language models (LLMs) to predict next-quarter chan...

Yu-Xiang Cheng, Nan-Jiang Du, Qi-Da Mou et al. · 0 citations
#artificial intelligence Preprint Sep 2026

AnalysisBank: An Expert Analysis Pattern Library for Financial Report Generation

AnalysisBank is proposed, which distills expert reports into a reusable library of Analyses, each pairing a data signal, an analytical move, and the expert span it was derived from, to operate at the analytical rather than structural level of financial report generation.

Ya-Jing Yang, Yun-Shan Ma, Kelvin J. L. Koa et al. · 0 citations
#artificial intelligence Preprint Aug 2026

BiasMix-Finance: Post-Generation KYC Guardrails for LLM Portfolio Advice

BiasMix-Finance (Mini) is introduced, a compact stress-test benchmark for constrained decision-making under biased LLM generations, with a 16-ETF universe, three investor profiles, and eight bias prompts, and the dataset, prompts, caps, and code are released.

Gaurav Kukreja, Parul Kukreja, Mohammed Abraar et al. · 0 citations
#artificial intelligence Review Sep 2026

FinancialAuditBench: Benchmark Construction under Differential Privacy Using Real-World Priors

FinancialAuditBench is introduced, a benchmark for evaluating agents on financial statement audit tasks, along with a framework for systematically generating synthetic engagements for model evaluation and training in privacy-sensitive domains.

Jerry Huang, Sarvesh Babu, Matt Van Buren et al. · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.