# Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models

arXiv: https://arxiv.org/abs/2402.03659 · HTML: https://mlsanity.com/paper/2402.03659/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 106 references that are in the map.
- First posted on arXiv 6 Feb 2024.

## Builds on (most cited first, 30 of 33)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [Universal Sentence Encoder](https://mlsanity.com/paper/1803.11175/) (2018)
- [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023)
- [Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog](https://mlsanity.com/paper/1907.00456/) (2019)
- [Sentiment Analysis in the Era of Large Language Models: A Reality Check](https://mlsanity.com/paper/2305.15005/) (2023)
- [A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction](https://mlsanity.com/paper/1704.02971/) (2017)
- [PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance](https://mlsanity.com/paper/2306.05443/) (2023)
- [Chain of Hindsight Aligns Language Models with Feedback](https://mlsanity.com/paper/2302.02676/) (2023)
- [Explore, Establish, Exploit: Red Teaming Language Models from Scratch](https://mlsanity.com/paper/2306.09442/) (2023)
- [Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization](https://mlsanity.com/paper/2308.02151/) (2023)
- [Temporal Relational Ranking for Stock Prediction](https://mlsanity.com/paper/1809.09441/) (2018)
- [Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method](https://mlsanity.com/paper/2310.00305/) (2023)
- [Listening to Chaotic Whispers: A Deep Learning Framework for News-oriented Stock Trend Prediction](https://mlsanity.com/paper/1712.02136/) (2017)

## Built on by (most cited first, 30 of 36)

- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [TradingAgents: Multi-Agents LLM Financial Trading Framework](https://mlsanity.com/paper/2412.20138/) (2024)
- [A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challenges](https://mlsanity.com/paper/2406.11903/) (2024)
- [Large Language Model Agent in Financial Trading: A Survey](https://mlsanity.com/paper/2408.06361/) (2024)
- [TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop](https://mlsanity.com/paper/2503.01013/) (2025)
- [Automate Strategy Finding with LLM in Quant Investment](https://mlsanity.com/paper/2409.06289/) (2024)
- [Harnessing Earnings Reports for Stock Predictions: A QLoRA-Enhanced LLM Approach](https://mlsanity.com/paper/2408.06634/) (2024)
- [AURORA:Automated Training Framework of Universal Process Reward Models via Ensemble Prompting and Reverse Verification](https://mlsanity.com/paper/2502.11520/) (2025)
- [LLM-Powered Multi-Agent System for Automated Crypto Portfolio Management](https://mlsanity.com/paper/2501.00826/) (2025)
- [Can LLM-based Financial Investing Strategies Outperform the Market in Long Run?](https://mlsanity.com/paper/2505.07078/) (2025)
- [Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression](https://mlsanity.com/paper/2505.19433/) (2025)
- [LiveTradeBench: Seeking Real-World Alpha with Large Language Models](https://mlsanity.com/paper/2511.03628/) (2025)
- [Agentic AI Systems Applied to tasks in Financial Services: Modeling and model risk management crews](https://mlsanity.com/paper/2502.05439/) (2025)
- [MASS: Muli-agent simulation scaling for portfolio construction](https://mlsanity.com/paper/2505.10278/) (2025)
- [ContestTrade: A Multi-Agent Trading System Based on Internal Contest Mechanism](https://mlsanity.com/paper/2508.00554/) (2025)
- [A Survey of Financial AI: Architectures, Advances and Open Challenges](https://mlsanity.com/paper/2411.12747/) (2024)
- [Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanations](https://mlsanity.com/paper/2502.12530/) (2025)
- [Bridging Language Models and Financial Analysis](https://mlsanity.com/paper/2503.22693/) (2025)
- [Integrating Large Language Models in Financial Investments and Market Analysis: A Survey](https://mlsanity.com/paper/2507.01990/) (2025)
- [Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading](https://mlsanity.com/paper/2510.04787/) (2025)
- [Empirical Asset Pricing with Large Language Model Agents](https://mlsanity.com/paper/2409.17266/) (2024)
- [QuantBench: Benchmarking AI Methods for Quantitative Investment](https://mlsanity.com/paper/2504.18600/) (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)
- [MEME: Modeling the Evolutionary Modes of Financial Markets](https://mlsanity.com/paper/2602.11918/) (2026)
- [Refined and Segmented Price Sentiment Indices from Survey Comments](https://mlsanity.com/paper/2411.09937/) (2024)
- [Exploring the Reliability of Self-explanation and its Relationship with Classification in Language Model-driven Financial Analysis](https://mlsanity.com/paper/2503.15985/) (2025)
- [From Natural Language to Executable Option Strategies via Large Language Models](https://mlsanity.com/paper/2603.16434/) (2026)
- [Fin-Analyst at FinMMEval 2026 Task 3: A Live Hybrid Trading Agent with LLM Specialists and Rule-Based Signals](https://mlsanity.com/paper/2607.12233/) (2026)
- [Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Making](https://mlsanity.com/paper/2602.11924/) (2026)
- [Generalized Stock Price Prediction for Multiple Stocks Combined with News Fusion](https://mlsanity.com/paper/2603.19286/) (2026)

## Abstract (arXiv)

Explaining stock predictions is generally a difficult task for traditional non-generative deep learning models, where explanations are limited to visualizing the attention weights on important texts. Today, Large Language Models (LLMs) present a solution to this problem, given their known capabilities to generate human-readable explanations for their decision-making process. However, the task of stock prediction remains challenging for LLMs, as it requires the ability to weigh the varying impacts of chaotic social texts on stock prices. The problem gets progressively harder with the introduction of the explanation component, which requires LLMs to explain verbally why certain factors are more important than the others. On the other hand, to fine-tune LLMs for such a task, one would need expert-annotated samples of explanation for every stock movement in the training set, which is expensive and impractical to scale. To tackle these issues, we propose our Summarize-Explain-Predict (SEP) framework, which utilizes a self-reflective agent and Proximal Policy Optimization (PPO) to let a LLM teach itself how to generate explainable stock predictions in a fully autonomous manner. The reflective agent learns how to explain past stock movements through self-reasoning, while the PPO trainer trains the model to generate the most likely explanations from input texts. The training samples for the PPO trainer are also the responses generated during the reflective process, which eliminates the need for human annotators. Using our SEP framework, we fine-tune a LLM that can outperform both traditional deep-learning and LLM methods in prediction accuracy and Matthews correlation coefficient for the stock classification task. To justify the generalization capability of our framework, we further test it on the portfolio construction task, and demonstrate its effectiveness through various portfolio metrics.