01
LLMs for Financial Advisement: A Fairness and Efficacy Study in Personal Decision Making
Discovered through citation/reference expansion; connected to 2 source papers.
The List / Categories
Professional, Regulatory, and Advisory Applications
Professional and regulatory applications include examinations, advisory tasks and compliance-related interpretation. Exam performance, professional competence and suitability for a real user are distinct outcomes.
How to read this literature
- Identify the jurisdiction, rule version, exam edition and evaluation date.
- Check source citations and escalation behavior when evidence is incomplete.
- Distinguish answer quality from workflow reliability and professional oversight requirements.
Use the reports and QA guides to inspect grounding, numerical reasoning and document provenance.
14 research papers
02
Can GPT models be Financial Analysts? An Evaluation of ChatGPT and GPT-4 on mock CFA Exams
This study evaluates ChatGPT and GPT-4 on mock CFA Level I and II exams, finding that GPT-4 with few-shot prompting can likely pass Level I and potentially Level II, while revealing significant limitations in calculation and complex reasoning.
03
Are Generative AI Agents Effective Personalized Financial Advisors?
A user study of 64 participants reveals that while LLM-advisors can match human experts in eliciting investment preferences, they often fail to resolve conflicting needs, and users exhibit a dangerous insensitivity to advice quality, preferring extroverted personas that provide worse financial guidance.
04
Can LLMs be Good Financial Advisors?: An Initial Study in Personal Decision Making for Optimized Outcomes
This study evaluates ChatGPT and Bard on 13 personal finance queries involving credit cards, bank accounts, and certificates of deposit, revealing that while outputs are fluent, both models suffer from significant mathematical errors, perceptual mistakes, and a lack of personalized, accurate financial advice.
05
Agentic AI Systems Applied to tasks in Financial Services: Modeling and model risk management crews
This paper implements and evaluates agentic crews using the CrewAI framework to automate financial modeling and model risk management (MRM) workflows, demonstrating robust performance in credit card fraud detection, approval, and portfolio risk tasks with human-in-the-loop oversight.
06
Large Language Model in Financial Regulatory Interpretation
This study demonstrates that GPT-4, when paired with image-based document loading and structured prompt engineering, can accurately interpret Basel III regulations and calculate minimum capital requirements, significantly outperforming other LLMs in both information extraction and complex mathematical computation.
07
Biased echoes: Large language models reinforce investment biases and increase portfolio risks of private investors
This study demonstrates that LLMs (ChatGPT, Gemini, Copilot) systematically increase portfolio risks for private investors across five dimensions—geographical, sector, trend chasing, active allocation, and expense risks—due to training data biases, with debiasing interventions only partially mitigating these effects.
08
A Preliminary Look at the State of the Art of Large Language Models on Chartered Financial Analyst Exams
This paper benchmarks 14 LLMs on CFA exams, finding that proprietary models pass Levels I and II but fail Level III essays, while open-source models like LLaMA 3 70B can pass Levels I and II with RAG assistance.
09
Advanced Financial Reasoning at Scale: Large Language Models on Chartered Financial Analyst Level III
This paper benchmarks 23 LLMs on CFA Level III exams, showing that frontier reasoning models like o4-mini pass the mock exam with 79.1% accuracy, though significant cost-latency trade-offs and human-LLM grading discrepancies persist.
10
Can Large Language Models Tackle the Chartered Financial Analyst Exam?
This study benchmarks GPT-4o, GPT-o1, and o3-mini on 1,560 CFA mock exam questions, demonstrating that reasoning-specialized models like GPT-o1 excel in financial analysis and that a novel domain-specific RAG pipeline significantly improves accuracy, particularly for complex, knowledge-intensive tasks.
11
DeepFinLLM: an intelligent financial advisor unleashing strategic insights with large language models
DeepFinLLM is an intelligent financial advisor that integrates the DeepSeek Chat V3 model with real-time data from the Financial Modeling Prep API to provide accurate, low-latency financial insights, achieving 94.2% accuracy and outperforming baselines like FinGPT and BloombergGPT on standard financial benchmarks.
12
A Multi-Agent Approach to Investor Profiling Using Large Language Models
Discovered through citation/reference expansion; connected to 1 source papers.
13
ChatGPT as a Financial Advisor: A Re-Examination
This qualitative study re-evaluates ChatGPT-4o and ChatGPT-5 against 21 personal finance scenarios, finding that while prompt engineering and model upgrades improve tone and numerical accuracy, the models still struggle with legal nuances, tax implications, and genuine empathy, positioning them as supportive rather than replacement tools for human advisors.
14
Model Risk Management in Finance: The Role of Agentic Systems in Risk Mitigation
Discovered through citation/reference expansion; connected to 2 source papers.