FinTradeBench benchmarks LLMs for financial reasoning combining company fundamentals and market signals.
problem Challenges in evaluating financial reasoning models for LLMs.
method Developed a benchmark integrating company fundamentals and trading signals, using a calibration-then-scaling framework.
result Clear performance gap between LLMs, retrieval improves reasoning over textual fundamentals but not trading signals.
ChatGPT improves financial reasoning, overcoming biases in gold investment.
problem Improving financial reasoning and overcoming biases in investment decisions.
method Applied advanced prompt engineering and semantic news information to enhance LLMs' performance.
result ChatGPT with CoT prompt provides more explainable predictions and higher investment returns.
REALFIN benchmarks financial reasoning by removing implicit assumptions, revealing model weaknesses.
problem Models struggle when implicit assumptions are missing, leading to incorrect answers.
method Developed a bilingual benchmark that systematically removes essential premises from financial questions.
result General-purpose models over-commit, while finance-specialized models fail to identify missing premises.
FinHEAR combines LLMs with human expertise for better financial decision-making.
problem Challenges in financial decision-making for language models.
method Multi-agent framework with specialized LLMs for historical analysis, event interpretation, and expert retrieval.
result FinHEAR outperforms baselines in financial tasks with higher accuracy and risk-adjusted returns.
Trading-R1 uses LLMs for financial trading, improving risk-adjusted returns.
problem Lack of interpretability and trust in AI for finance.
method Supervised fine-tuning and reinforcement learning with a curriculum.
result Improved risk-adjusted returns and lower drawdowns compared to other models.
FinReflectKG benchmarks financial QA by linking relevant context from a financial KG, improving model performance and efficiency.
problem Efficiently retrieving and navigating relevant financial information across diverse sources and years.
method A benchmark built on a temporally indexed financial KG, generating QA pairs via pattern-specific prompts and quality control, evaluating retrieval scenarios.
result KG-guided retrieval yields substantial gains in correctness and token utilization, improving model performance by 24%.
PyFi uses adversarial agents to train VLMs on financial image understanding.
problem Training VLMs to understand complex financial questions.
method PyFi-600K dataset and adversarial MCTS mechanism.
result Fine-tuned VLMs improve by 19.52% and 8.06% on financial question accuracy.
FinCARE combines financial data and AI reasoning to improve causal analysis of financial performance.
problem Correlation-based analysis fails to capture true causal relationships in financial performance.
method Hybrid framework integrating causal discovery algorithms with financial domain knowledge from SEC filings and LLM reasoning.
result KG+LLM-enhanced methods improve causal discovery across PC, GES, and NOTEARS by 36-366%.
FinMaster benchmarks LLMs in financial tasks, revealing gaps in reasoning.
problem Challenges in financial tasks, including labor-intensive processes and low error tolerance.
method Developed a comprehensive financial benchmark (FinMaster) with three modules: FinSim, FinSuite, and FinEval.
result LLMs struggle with complex financial reasoning, showing significant accuracy drops.
Trade-R1 bridges verifiable rewards to stochastic financial markets via process-level reasoning verification.
problem Extending RL to financial markets where rewards are verifiable but noisy.
method A verification method that transforms reasoning over financial documents into a structured RAG task, using a triangular consistency metric.
result DSR achieves superior cross-market generalization while maintaining reasoning consistency.
A new explainable CBR system predicts financial risks with interpretability and good performance.
problem Predicting financial risks with interpretability and good performance.
method A novel explainable case-based reasoning (CBR) approach.
result The CBR system provides a good prediction performance and interpretability.
Paper uses LLMs for financial forecasting, overcoming sequence reasoning and multi-modal challenges.
problem Challenges in financial time series forecasting, especially cross-sequence reasoning and multi-modal signals.
method Combines LLMs with financial data and news, using zero-shot/few-shot inference and instruction-based fine-tuning.
result LLMs can offer explainable financial forecasts, leveraging cross-sequence reasoning and multi-modal information.
LLMs struggle with financial reasoning but can outperform the market with human oversight.
problem Financial reasoning failures in LLM-generated stock market predictions.
method Evaluated four LLMs using three prompting strategies and compared to human oversight.
result LLMs require human oversight to fully realize their potential in financial markets.
VERAFI improves financial AI by verifying calculations and compliance.
problem Financial AI systems generate errors and violations during reasoning.
method VERAFI combines dense retrieval, reranking, and automated reasoning policies.
result VERAFI achieves 94.7% factual correctness, 81% relative improvement.
UniFinEval benchmarks financial models across text, images, and videos.
problem Challenges in evaluating financial multimodal models across text, images, and videos.
method Proposes UniFinEval, a unified multimodal benchmark for financial scenarios.
result Gemini-3-pro-preview achieves best performance but still lags behind experts.
Novel financial time-series data representation improves industry sector classification.
problem Classifying industries using historical stock returns time-series data.
method Proposed a novel representation based on stock returns embeddings for time-series data, overcoming representational challenges of conventional approaches.
result Substantial performance improvements over baselines using conventional representations.
VTA combines verbal and latent reasoning for accurate stock time-series forecasts.
problem Challenges in combining textual analysis with time-series data for financial forecasting.
method Converts stock price data into textual annotations, optimizes reasoning trace using inverse MSE, conditions time-series model outputs on reasoning attributes.
result VTA achieves state-of-the-art forecasting accuracy and interpretable reasoning traces.
LLMs detect market patterns through causal reasoning, not just temporal association.
problem Detecting structural market patterns in financial data.
method Obfuscation testing using the WHO-WHOM-WHAT framework.
result LLMs achieve 71.5% detection rate of market patterns without temporal context.
Survey of financial foundation models for diverse applications.
problem Challenges in applying general-purpose FMs to financial tasks.
method Review of financial foundation models (FFMs) in three modalities.
result Emergence of FFMs designed specifically for finance.
We extend Kirman's model by introducing variable event time scale. The proposed flexible time scale is equivalent to the variable trading activity observed in financial markets. Stochastic version of the extended Kirman's agent based model is compared to the non-linear stochastic models of long-range memory in financia…
Benchmark evaluates financial misinformation detection models, revealing weaknesses without external context.
problem Detecting financial misinformation without external references.
method RFC Bench at paragraph level, two tasks: reference-free detection and comparison-based diagnosis.
result Performance improves with comparative context, revealing model weaknesses in reference-free settings.
Study evaluates LLMs like ChatGPT and GPT-4 on financial analysis tasks.
problem Assessing financial reasoning capabilities of large language models.
method Mock CFA exam questions, Zero-Shot, Chain-of-Thought, Few-Shot scenarios.
result LLMs perform well on financial analysis tasks, but have limitations.
Agent Trading Arena trains LLMs in real-time financial markets to improve numerical reasoning.
problem Limited real-world training for LLMs in financial markets.
method Virtual zero-sum stock market with competitive multi-agent trading.
result LLMs perform better with chart-based visualizations and a reflection module.
I summarize the recent work on market (in)efficiency, highlighting key elements why financial markets will never be made efficient. My approach is not by adding more empirical evidence, but giving plausible reasons as to where inefficiency arises and why it's not rational to arbitrage it away.
Study shows GPT's earnings forecasts are human-like but not always accurate.
problem Information friction in AI-generated financial analysis.
method Examined GPT's earnings forecasts following corporate earnings releases and proposed a diagnostic framework.
result GPT's narrative attention is consistent and human-like but not always associated with higher forecast accuracy.
Principles of financial product synthesis from a few basic financial products constitute an interesting research topic inspired by Islamic finance. We make an effort to answer general questions that should be answered before starting to investigate the main issues concerning this topic with the formalization of financi…
This summarizes the study of the financial and economic crisis in Europe. The starting questions were: 1) Why do we have a crisis? Unde venis? 2) What will be the outcome? Quo vadis? Here is the reasoning which touches many areas, ranging from financial to politics and from psychology and economy.
EDINET-Bench evaluates LLMs on complex financial tasks using Japanese financial statements.
problem Challenges in evaluating LLMs on financial tasks due to specialized expertise and scarce benchmarks.
method Developed EDINET-Bench, an open-source Japanese financial benchmark for LLMs on tasks like fraud detection and earnings forecasting.
result State-of-the-art LLMs perform only marginally better than logistic regression in financial tasks, highlighting the need for more realistic benchmarks.
FinZero improves financial time series forecasting accuracy with multimodal modeling.
problem Lack of interpretability, uncertainty, and scalability in financial time series forecasting.
method Developed a multimodal pre-trained model FinZero using UARPO method for reasoning, prediction, and uncertainty analysis.
result FinZero achieves an approximate 13.48% improvement in prediction accuracy over GPT-4o in high-confidence group.
The St. Petersburg Paradox, an important topic in probability theory, has not been solved in the last 280 years. Since Nicolaus Bernoulli proposed the St. Petersburg Paradox in 1738, many people had tried to solve it and had proposed various explanations, but all were not satisfactory. In this paper we propose a new pr…
PandaAI: A practical agent for neuro-symbolic data analysis and decision-making in finance
problem Sequential decision-making in finance
method Leveraging LLMs for market regime modeling and constrained alpha generation
result PandaAI achieves higher Rank IC and lower maximum drawdown
The latest financial crisis has painfully revealed the dangers arising from a globally interconnected financial system. Conventional approaches based on the notion of the existence of equilibrium and those which rely on statistical forecasting have seen to be inadequate to describe financial systems in any reasonable w…
Paper develops framework for AI agents in financial markets.
problem Systemic implications of AI in finance depend on agent architectures.
method Four-layer architecture and AFMM model for analysis.
result AI agents can improve market efficiency and resilience.
Digital Financial Services continue to expand and replace the delivery of traditional banking services to the customers through innovative technologies to meet the growing complex needs and globalization challenges. These diversified digital products help the organizations (service providers) to improve their firm perf…
Unified LLM-agent with RL improves financial trading performance.
problem LLMs struggle with complex, multi-step financial tasks.
method Fusion of LLMs and gradient-based RL for policy optimization.
result Improves LLM performance in trading and other financial tasks.
Study benchmarks LLMs in portfolio optimization tasks.
problem Evaluate financial decision-making of LLMs.
method Mathematically explicit portfolio optimization problems with multiple-choice questions.
result Distinct performance patterns among LLMs in different financial tasks.
Shapley values explain financial language models, aligning with domain knowledge.
problem Lack of explainability in financial applications of large language models.
method Shapley value analysis for financial textual data.
result Shapley values provide consistent explanations with financial reasoning.
This paper illustrates a procedure for fitting financial data with α-stable distributions. After using all the available methods to evaluate the distribution parameters, one can qualitatively select the best estimate and run some goodness-of-fit tests on this estimate, in order to quantitatively assess its quality. I…
Study proposes a data-driven CBR system for improved bankruptcy prediction.
problem Lack of interpretability in machine learning models for bankruptcy prediction.
method Data-driven explainable case-based reasoning (CBR) system.
result Proposed CBR system outperforms existing CBR and machine learning models.
Nowadays, financial data analysis is becoming increasingly important in the business market. As companies collect more and more data from daily operations, they expect to extract useful knowledge from existing collected data to help make reasonable decisions for new customer requests, e.g. user credit category, confide…
We investigate whether fractal markets hypothesis and its focus on liquidity and invest- ment horizons give reasonable predictions about dynamics of the financial markets during the turbulences such as the Global Financial Crisis of late 2000s. Compared to the mainstream efficient markets hypothesis, fractal markets hy…
We consider a discounted reward control problem in continuous time stochastic environment where the discount rate might be an unbounded function of the control process. We provide a set of general assumptions to ensure that there exists a smooth classical solution to the corresponding HJB equation. Moreover, some verif…
Financial fraud detection in digital banking requires reasoning over multiple heterogeneous event streams.
problem Financial fraud detection in digital banking requires reasoning over multiple heterogeneous event streams.
method Multi-Stream Fraud Transformer (MSFT) architecture that encodes each event stream with independent Transformer encoders and fuses their representations through configurable mechanisms.
result Sequence models significantly outperform gradient-boosted trees operating on aggregated features.
Paper develops a new similarity metric for predicting stock market returns.
problem Predicting stock returns is challenging due to market stochasticity and various influencing factors.
method Case-based reasoning approach using historical pricing data and a novel similarity metric.
result Demonstrates the benefits of the novel similarity metric in predicting stock market returns.
AGENTICAITA uses AI agents to autonomously trade markets without human intervention.
problem Inability of traditional trading systems to adapt to market complexity.
method Introduces an agentic AI framework with specialized LLM agents reasoning, negotiating, and acting.
result Demonstrated operational correctness and non-trivial inter-agent negotiation in live market conditions.
FINCH dataset enables financial Text-to-SQL tasks, improving model evaluation.
problem Lack of a large-scale financial dataset for Text-to-SQL tasks.
method Curated financial dataset (FINCH), benchmarking reasoning and language models.
result Proposed FINCH Score for more accurate financial model evaluation.
Generative AI agents improve ERP systems by automating complex financial tasks.
problem Static, rule-based workflows limit adaptability and intelligence in ERP systems.
method Introducing Generative Business Process AI Agents (GBPAs) that integrate generative AI with business process modeling and multi-agent orchestration.
result GBPAs achieve up to 40% reduction in processing time and 94% drop in error rate.
InvestorBench benchmarks LLM agents in financial tasks.
problem Lack of a comprehensive benchmark for LLM-based financial agents.
method Developed a benchmark with diverse financial tasks and datasets.
result Evaluated LLM agents' performance across various financial products and market environments.