# Financial Statement Analysis with Large Language Models

arXiv: https://arxiv.org/abs/2407.17866 · HTML: https://mlsanity.com/paper/2407.17866/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2024.

## Built on by (most cited first, 30 of 31)

- [MarketSenseAI 2.0: Enhancing Stock Analysis through LLM Agents](https://mlsanity.com/paper/2502.00415/) (2025)
- [Visual Structures Helps Visual Reasoning: Addressing the Binding Problem in VLMs](https://mlsanity.com/paper/2506.22146/) (2025)
- [Standard Benchmarks Fail -- Auditing LLM Agents in Finance Must Prioritize Risk](https://mlsanity.com/paper/2502.15865/) (2025)
- [Replay Failures as Successes: Sample-Efficient Reinforcement Learning for Instruction Following](https://mlsanity.com/paper/2512.23457/) (2025)
- [Belief in the Machine: Investigating Epistemological Blind Spots of Language Models](https://mlsanity.com/paper/2410.21195/) (2024)
- [EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements](https://mlsanity.com/paper/2506.08762/) (2025)
- [Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models](https://mlsanity.com/paper/2509.21155/) (2025)
- [FinTexTS: Financial Text-Paired Time-Series Dataset via Semantic-Based and Multi-Level Pairing](https://mlsanity.com/paper/2603.02702/) (2026)
- [Can AI Help with Your Personal Finances?](https://mlsanity.com/paper/2412.19784/) (2024)
- [Bridging Language Models and Financial Analysis](https://mlsanity.com/paper/2503.22693/) (2025)
- [Cognitive Agents Powered by Large Language Models for Agile Software Project Management](https://mlsanity.com/paper/2508.16678/) (2025)
- [Behavioral Bias of Vision-Language Models: A Behavioral Finance View](https://mlsanity.com/paper/2409.15256/) (2024)
- [Evaluating Large Language Models on Financial Report Summarization: An Empirical Study](https://mlsanity.com/paper/2411.06852/) (2024)
- [Meeseeks: A Feedback-Driven, Iterative Self-Correction Benchmark evaluating LLMs' Instruction Following Capability](https://mlsanity.com/paper/2504.21625/) (2025)
- [UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models](https://mlsanity.com/paper/2410.14059/) (2024)
- [FinSphere, a Real-Time Stock Analysis Agent Powered by Instruction-Tuned LLMs and Domain Tools](https://mlsanity.com/paper/2501.12399/) (2025)
- [Evaluating Large Language Models (LLMs) in Financial NLP: A Comparative Study on Financial Report Analysis](https://mlsanity.com/paper/2507.22936/) (2025)
- [Multimodal Language Models with Modality-Specific Experts for Financial Forecasting from Interleaved Sequences of Text and Time Series](https://mlsanity.com/paper/2509.19628/) (2025)
- [Exploring the Synergy of Quantitative Factors and Newsflow Representations from Large Language Models for Stock Return Prediction](https://mlsanity.com/paper/2510.15691/) (2025)
- [When Certainty Is an Artifact: Keyword Lexicon Blindness and the (Mis)Measurement of Rhetorical Stance](https://mlsanity.com/paper/2606.26062/) (2026)
- [Deriving Strategic Market Insights with Large Language Models: A Benchmark for Forward Counterfactual Generation](https://mlsanity.com/paper/2505.19430/) (2025)
- [VTS-Guided AI Interaction Workflow for Business Insights](https://mlsanity.com/paper/2507.00347/) (2025)
- [Towards Human-Centered RegTech: Unpacking Professionals' Strategies and Needs for Using LLMs Safely](https://mlsanity.com/paper/2510.01638/) (2025)
- [Integrating Large Language Models and Reinforcement Learning for Sentiment-Driven Quantitative Trading](https://mlsanity.com/paper/2510.10526/) (2025)
- [UniFinEval: Towards Unified Evaluation of Financial Multimodal Models across Text, Images and Videos](https://mlsanity.com/paper/2601.22162/) (2026)
- [MemGuard-Alpha: Limits of Membership Inference for Detecting and Filtering Memorization-Contaminated Signals in LLM-Based Financial Forecasting](https://mlsanity.com/paper/2603.26797/) (2026)
- [YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition](https://mlsanity.com/paper/2606.05868/) (2026)
- [CSTrader: A Testbed for Language-Grounded Trading in a Community-Driven Virtual Asset Market](https://mlsanity.com/paper/2606.31461/) (2026)
- [Can Open-Weight Models Compete on Financial Text Comprehension?](https://mlsanity.com/paper/2608.08634/) (2026)
- [The Public Discourse Corpus (PDC): A Speaker-Attributed Dataset for Valence and Epistemic Modality with Target Speaker Participation](https://mlsanity.com/paper/2609.20232/) (2026)

## Abstract (arXiv)

We investigate whether large language models (LLMs) can successfully perform financial statement analysis in a way similar to a professional human analyst. We provide standardized and anonymous financial statements to GPT4 and instruct the model to analyze them to determine the direction of firms' future earnings. Even without narrative or industry-specific information, the LLM outperforms financial analysts in its ability to predict earnings changes directionally. The LLM exhibits a relative advantage over human analysts in situations when the analysts tend to struggle. Furthermore, we find that the prediction accuracy of the LLM is on par with a narrowly trained state-of-the-art ML model. LLM prediction does not stem from its training memory. Instead, we find that the LLM generates useful narrative insights about a company's future performance. Lastly, our trading strategies based on GPT's predictions yield a higher Sharpe ratio and alphas than strategies based on other models. Our results suggest that LLMs may take a central role in analysis and decision-making.