Skip to content

Integrating large language models in financial investments and market analysis: A survey

Authors: Sedigheh Mahdavi; Jiating; Chen; Pradeep Kumar Joshi; Lina Huertas Guativa; Upmanyu Singh
Year: 2025
Venue: arXiv preprint

type: survey collection: sok-references status: auto

Links: arXiv:2507.01990

Summary

Auto-extracted summary (unreviewed)

This survey reviews how LLMs are being used for financial investment and market analysis, organizing the literature into four frameworks: LLM-based pipelines, hybrid integration with traditional financial models, fine-tuning/adaptation approaches, and multi-agent architectures. It covers applications in stock selection, risk assessment, sentiment analysis, trading and forecasting, the enabling techniques (RAG, chain-of-thought, in-context learning, PEFT/LoRA), and closes with open directions such as adaptive fine-tuning and finance-specific LLM architectures.

Abstract

Large Language Models (LLMs) have been employed in financial decision making, enhancing analytical capabilities for investment strategies. Traditional investment strategies often utilize quantitative models, fundamental analysis, and technical indicators. However, LLMs have introduced new capabilities to process and analyze large volumes of structured and unstructured data, extract meaningful insights, and enhance decision-making in real-time. This survey provides a structured overview of recent research on LLMs within the financial domain, categorizing research contributions into four main frameworks: LLM-based Frameworks and Pipelines, Hybrid Integration Methods, Fine-Tuning and Adaptation Approaches, and Agent-Based Architectures. This study provides a structured review of recent LLMs research on applications in stock selection, risk assessment, sentiment analysis, trading, and financial forecasting. By reviewing the existing literature, this study highlights the capabilities, challenges, and potential directions of LLMs in financial markets.
Source: arxiv

Extracted details

Field Value Source Confidence
contribution Taxonomy of LLM-in-finance research into four frameworks (pipelines, hybrid, fine-tuning, agent-based) llm 0.85
contribution Structured review of applications: stock selection, risk assessment, sentiment analysis, trading, financial forecasting llm 0.85
contribution Overview of enabling techniques (RAG, CoT, ICL, PEFT/LoRA) and datasets used in reviewed studies llm 0.85
contribution Discussion of challenges and future research directions llm 0.85
models GPT-4 llm 0.85
models GPT-InvestAR llm 0.85
models StockGPT llm 0.85
datasets S&P 500 llm 0.85
tasks stock selection llm 0.85
tasks risk assessment llm 0.85
tasks sentiment analysis llm 0.85
tasks trading llm 0.85
tasks financial forecasting llm 0.85
tasks portfolio optimization llm 0.85
limitations Fine-tuned financial LLMs struggle to adapt to evolving market conditions llm 0.85
limitations General-purpose LLMs are not optimized for financial time-series reasoning or multimodal financial data fusion llm 0.85

SoK reference [3]

S. Mahdavi, P. K. Joshi, L. H. Guativa, U. Singh et al., “Integrating large language models in financial investments and market analysis: A survey,” arXiv preprint arXiv:2507.01990, 2025.

Listed on the reference page of the site.

Keyword mentions

Counts of vocabulary terms in the full text (first page of occurrence in brackets).

  • library: PyTorch 1 [p.4], TensorFlow 1 [p.4]
  • model: GPT 62 [p.3], LLaMA 22 [p.5], LoRA 10 [p.1], Mixture of experts 7 [p.3], CNN 6 [p.6], Transformer 4 [p.6], Random forest 2 [p.11], RNN / LSTM 1 [p.6], Logistic regression 1 [p.11]
  • technique: Fine-tuning 14 [p.1]
  • task: Finance 36 [p.1], Sentiment analysis 12 [p.1]
  • topic: Large language models 171 [p.1], Benchmark 4 [p.7]

Files

Path (under papers/) Collection Pages Size SHA-256 Note
references/sok-references/003_integrating-large-language-models-in-financial-investments-a.pdf sok-references 21 219.1 KB 82466aa920e3

Database key: integrating-large-language-models-in-financial-investments-and-market · created 2026-11-05 · updated 2026-11-05 · edit with python3 tools/paperdb.py set integrating-large-language-models-in-financial-investments-and-market COLUMN VALUE