{"paper_id":"2402.03659","title":"Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models","authors":["Kelvin J. L. Koa","Yunshan Ma","Ritchie Ng","Tat-Seng Chua"],"paper_date":"2024-02-06","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2402.03659v3","page_url":"https://thequant.space/flowcharts/learning-to-generate-explainable-stock-predictions-using-sel/","scores":{"empirical_rigor":8,"math_complexity":3,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes the Summarize-Explain-Predict (SEP) framework that uses a self‑reflective agent and Proximal Policy Optimization to let a large language model autonomously generate explainable stock predictions.","quote":"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.","summary":"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…","strategy":null},"assumptions":{"status":"none_found","items":[]},"datasets":{"status":"available","items":[{"name":"updated StockNet dataset (2020–2022)","provider":null,"kind":"text-news","access":"public","period":"2020–2022","universe":"top 5 stocks in 11 industries (55 stocks total)","quote":"We collect data for the top 5 stocks in the 11 industries, giving us a total of 55 stocks. The price data is collected from Yahoo Finance"}],"known":[{"id":"twitter","name":"Twitter / X","provider":"X Corp.","kind":"text-news","access":"public","quote":"The price data is collected from Yahoo Finance1, while the tweet data is collected using the Twitter API2.","mentions":1,"used_in":1},{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"The price data is collected from Yahoo Finance1, while the tweet data is collected using the Twitter API2.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"SEP fine‑tuned on GPT‑generated explanations achieves a 2.4% improvement in prediction accuracy over the strongest baseline (GRU+Att) when using all texts.","kind":"predictive-accuracy","quote":"... was able to obtain the best results, achieving an improvement of 2.4% over the strongest baseline (GRU+Att) using all texts."},{"finding":"SEP outperforms all other methods on most portfolio metrics, achieving the highest Sharpe Ratio (1.150) among the compared approaches.","kind":"performance","quote":"Our SEP model was able to outperform all other methods in most portfolio metrics, and achieve comparable performance in its standard deviation, which showcases the effectiveness of our SEP framework."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":30,"citations":{"cited_by_in_corpus":34,"by_independent_authors":31,"how_cited":{"used_as_baseline":0,"uses_method_or_data":5,"extends":0,"discusses_findings":0,"mentions":18,"unclassified":11},"independent_papers":[{"paper":{"paper_id":"2505.07078","title":"Can LLM-based Financial Investing Strategies Outperform the Market in Long Run?","paper_date":"2025-05-11","authors":["Weixian Waylon Li","Hyeonjun Kim","Mihai Cucuringu","Tiejun Ma"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/can-llm-based-financial-investing-strategies-outperform-the/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2412.20138","title":"TradingAgents: Multi-Agents LLM Financial Trading Framework","paper_date":"2024-12-28","authors":["Yijia Xiao","Edward Sun","Di Luo","Wei Wang"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/tradingagents-multi-agents-llm-financial-trading-framework/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2508.00554","title":"ContestTrade: A Multi-Agent Trading System Based on Internal Contest Mechanism","paper_date":"2025-08-01","authors":["Li Zhao","Rui Sun","Zuoyou Jiang","Bo Yang","Yuxiao Bai","Mengting Chen"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/contesttrade-a-multi-agent-trading-system-based-on-internal/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2510.15691","title":"Exploring the Synergy of Quantitative Factors and Newsflow Representations from Large Language Models for Stock Return Prediction","paper_date":"2025-10-17","authors":["Tian Guo","Emmanuel Hauptmann"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/exploring-the-synergy-of-quantitative-factors-and-newsflow-r/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2408.06361","title":"Large Language Model Agent in Financial Trading: A Survey","paper_date":"2024-07-26","authors":["Han Ding","Yinheng Li","Junhao Wang","Hang Chen","Doudou Guo","Yunbai Zhang"],"empirical_rigor":5.5,"page_url":"https://thequant.space/flowcharts/large-language-model-agent-in-financial-trading-a-survey/"},"how":"uses_method_or_data","quote":null}],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/koa-fin/sep","note":null},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T16:28:08Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}