mlsanityData to 7 Oct 2026

AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Framework

arXiv 2403.12582 ↗First posted 19 Mar 2024cs.CLcited by 47

On the map: Retrieval-augmented generation → Legal and financial RAG

Abstract (arXiv)

The task of financial analysis primarily encompasses two key areas: stock trend prediction and the corresponding financial question answering. Currently, machine learning and deep learning algorithms (ML&DL) have been widely applied for stock trend predictions, leading to significant progress. However, these methods fail to provide reasons for predictions, lacking interpretability and reasoning processes. Also, they can not integrate textual information such as financial news or reports. Meanwhile, large language models (LLMs) have remarkable textual understanding and generation ability. But due to the scarcity of financial training datasets and limited integration with real-time knowledge, LLMs still suffer from hallucinations and are unable to keep up with the latest information. To tackle these challenges, we first release AlphaFin datasets, combining traditional research datasets, real-time financial data, and handwritten chain-of-thought (CoT) data. It has a positive impact on training LLMs for completing financial analysis. We then use AlphaFin datasets to benchmark a state-of-the-art method, called Stock-Chain, for effectively tackling the financial analysis task, which integrates retrieval-augmented generation (RAG) techniques. Extensive experiments are conducted to demonstrate the effectiveness of our framework on financial analysis.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). Placed in Legal and financial RAG, one of 15 directions in Retrieval-augmented generation. Builds on 16 of its 27 references that are in the map. First posted on arXiv 19 Mar 2024.

Builds on

16 of 27 references.

References · 16

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  5. 2023BloombergGPT: A Large Language Model for Financecited by 923
  6. 2019FinBERT: Financial Sentiment Analysis with Pre-trained Language Modelscited by 378
  7. 2013Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Textscited by 310
  8. 2023PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Financecited by 217
  9. 2022SGPT: GPT Sentence Embeddings for Semantic Searchcited by 204
  10. 2022ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answeringcited by 194
  11. 2022A Survey on Retrieval-Augmented Text Generationcited by 157
  12. 2023Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigationcited by 123
4 more
  1. 2018Retrieve and Refine: Improved Sequence Generation Models For Dialoguecited by 82
  2. 2020Impact of News on the Commodity Market: Dataset and Resultscited by 80
  3. 2021Neural Machine Translation with Monolingual Translation Memorycited by 61
  4. 2021PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generationcited by 37

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 11; 2025: 25; 2026: 11.

47 papers.

Sort:

By area:

  1. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
  2. 2024A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challengescited by 86
  3. 2025Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learningcited by 82
  4. 2025Evaluating Step-by-step Reasoning Traces: A Surveycited by 62
  5. 2024MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPscited by 45
  6. 2025R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimizationcited by 39
  7. 2024OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domaincited by 28
  8. 2025Multi-modal Time Series Analysis: A Tutorial and Surveycited by 24
  9. 2025Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queriescited by 19
  10. 2025FinMTEB: Finance Massive Text Embedding Benchmarkcited by 18
  11. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Surveycited by 18
  12. 2025Standard Benchmarks Fail -- Auditing LLM Agents in Finance Must Prioritize Riskcited by 13
35 more
  1. 2024Do We Need Domain-Specific Embedding Models? An Empirical Investigationcited by 12
  2. 2026QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Miningcited by 12
  3. 2024TradExpert: Revolutionizing Trading with Mixture of Expert LLMscited by 11
  4. 2024AI in Investment Analysis: LLMs for Equity Stock Ratingscited by 10
  5. 2024Fine-Tuning Large Language Models for Stock Return Prediction Using Newsflowcited by 8
  6. 2025PROPHET: An Inferable Future Forecasting Benchmark with Causal Intervened Likelihood Estimationcited by 8
  7. 2026TSAQA: Time Series Analysis Question And Answering Benchmarkcited by 8
  8. 2025FactorGCL: A Hypergraph-Based Factor Model with Temporal Residual Contrastive Learning for Stock Returns Predictioncited by 7
  9. 2025Towards Temporal-Aware Multi-Modal Retrieval Augmented Generation in Financecited by 7
  10. 2025Retrieval-Augmented Purifier for Robust LLM-Empowered Recommendationcited by 7
  11. 2024A Survey of Financial AI: Architectures, Advances and Open Challengescited by 6
  12. 2025Exposing Product Bias in LLM Investment Recommendationcited by 6
  13. 2025Agentar-Fin-R1: Enhancing Financial Intelligence through Domain Expertise, Training Efficiency, and Advanced Reasoningcited by 5
  14. 2025Integrating Large Language Models in Financial Investments and Market Analysis: A Surveycited by 4
  15. 2025Advancing Financial Engineering with Foundation Models: Progress, Applications, and Challengescited by 4
  16. 2025FinKario: Event-Enhanced Automated Construction of Financial Knowledge Graphcited by 4
  17. 2026From Feedback Loops to Policy Updates: Reinforcement Fine-Tuning for LLM-Based Alpha Factor Discoverycited by 4
  18. 2025LLMs for Supply Chain Managementcited by 2
  19. 2025MetaGraph: A Large-Scale Meta-Analysis of GenAI in Financial NLP (2022-2025)cited by 2
  20. 2024Adversarial Databases Improve Success in Retrieval-based Large Language Modelscited by 1
  21. 2024CAP: Data Contamination Detection via Consistency Amplificationcited by 1
  22. 2025FinTSBridge: A New Evaluation Suite for Real-world Financial Prediction with Advanced Time Series Modelscited by 1
  23. 2025AI Analyst: Framework and Comprehensive Evaluation of Large Language Models for Financial Time Series Report Generationcited by 1
  24. 2025Exploring the Synergy of Quantitative Factors and Newsflow Representations from Large Language Models for Stock Return Predictioncited by 1
  25. 2026Janus-Q: End-to-End Event-Driven Trading via Hierarchical-Gated Reward Modelingcited by 1
  26. 2026CN-Buzz2Portfolio: A Chinese-Market Dataset and Benchmark for LLM-Based Macro and Sector Asset Allocation from Daily Trending Financial Newscited by 1
  27. 2026Moira: Language-driven Hierarchical Reinforcement Learning for Pair Tradingcited by 1
  28. 2026K-FinHallu: A Hallucination Detection Benchmark for Multi-Turn RAG in Korean Financecited by 1
  29. 2025H3M-SSMoEs: Hypergraph-based Multimodal Learning with LLM Reasoning and Style-Structured Mixture of Expertscited by 0
  30. 2025TopicProphet: Prophesies on Temporal Topic Trends and Stockscited by 0
  31. 2025SPAR: Session-based Pipeline for Adaptive Retrieval on Legacy File Systemscited by 0
  32. 2026BizFinBench.v2: Towards Reliable LLMs in Finance via Real-User Data and Offline/Online Bilingual Evaluationcited by 0
  33. 2026UniFinEval: Towards Unified Evaluation of Financial Multimodal Models across Text, Images and Videoscited by 0
  34. 2026MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integrationcited by 0
  35. 2026CSTrader: A Testbed for Language-Grounded Trading in a Community-Driven Virtual Asset Marketcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Automated Summarization of Financial News Using Large Language Models and Retrieval-Augmented Generation: An Early Empirical Study (Fall 2023)
  2. 2024FinBen: A Holistic Financial Benchmark for Large Language Models
  3. 2024RAG-IT: Retrieval-Augmented Instruction Tuning for Automated Financial Analysis -- A Case Study for the Semiconductor Sector
  4. 2025FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation
  5. 2024Aligning LLMs with Human Instructions and Stock Market Feedback in Financial Sentiment Analysis
  6. 2025Retrieval-augmented Large Language Models for Financial Time Series Forecasting
  7. 2023Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language Models
  8. 2026Evaluating Financial Intelligence in Large Language Models: Benchmarking SuperInvesting AI with LLM Engines