{"paper_id":"2306.06031","title":"FinGPT: Open-Source Financial Large Language Models","authors":["Hongyang Yang","Xiao-Yang Liu","Christina Dan Wang"],"paper_date":"2023-06-09","paper_type":"software-tool","paper_url":"https://arxiv.org/pdf/2306.06031v2","page_url":"https://thequant.space/flowcharts/fingpt-open-source-financial-large-language-models/","scores":{"empirical_rigor":8,"math_complexity":3,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes FinGPT, an open-source large language model for finance built with a data‑centric approach and lightweight low‑rank adaptation.","quote":"we present an open-source large language model, FinGPT, for the finance sector.","summary":"Large language models (LLMs) have shown the potential of revolutionizing natural language processing tasks in diverse domains, sparking great interest in finance. Accessing high-quality financial data is the first challenge for financial LLMs (FinLLMs). While proprietary models like BloombergGPT…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Sentiment labels derived from short‑term price movements accurately reflect market sentiment.","type":"data","stated":"explicit","quote":"Market-driven labels (self-labeled data) strongly improve real‑world applicability;"},{"assumption":"Low‑rank adaptation (LoRA) can replace full fine‑tuning with comparable performance.","type":"model","stated":"explicit","quote":"LoRA reduces adaptation cost by ∼1000× compared to full fine‑tuning;"},{"assumption":"Reinforcement Learning on Stock Prices (RLSP) aligns model outputs with actual market reactions.","type":"model","stated":"explicit","quote":"RLSP incorporates financial market feedback, distinguishing FinGPT from traditional supervised models."},{"assumption":"The financial news dataset collected via the FinGPT pipeline is clean and representative of market information.","type":"data","stated":"implied","quote":"We utilize a large‑scale financial news sentiment dataset curated through the FinGPT real‑time data pipeline."}]},"datasets":{"status":"available","items":[{"name":"large‑scale financial news sentiment dataset","provider":"FinGPT real‑time data pipeline","kind":"text-news","access":"public","period":"2016–2024","universe":null,"quote":"The dataset contains: • Over 620,000 cleaned financial news headlines; • Sources including CNBC, Reuters, Yahoo Finance, MarketWatch, etc., collected through the FinNLP pipeline; • Time span from 2016–2024;"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"The dataset contains: • Over 620,000 cleaned financial news headlines; • Sources including CNBC, Reuters, Yahoo Finance, Mar-ketWatch, etc., collected through the FinNLP pipeline; • Time span from 2016–2024; • Market-driven labels generated using short-term price movement: label =    Positive, r > θp Negative, r < −θn Neutral, |r| ≤θ where r denotes the stock’s percentage price change fol-lowing the news.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"none"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"none","findings":[{"finding":"FinGPT (SFT+RLSP) achieves 82.1% accuracy and 80.9% macro‑F1, outperforming all baselines.","kind":"performance","quote":"FinGPT (SFT+RLSP) 82.1 80.9 83.4 81.5 77.8"},{"finding":"FinGPT (LoRA‑SFT) reaches 78.8% accuracy and 77.3% macro‑F1, beating FinBERT and other models.","kind":"performance","quote":"FinGPT (LoRA‑SFT) 78.8 77.3 79.6 76.8 75.4"},{"finding":"LoRA provides most of the performance gain, while RLSP adds further improvement.","kind":"performance","quote":"Ablation Study LoRA performs most of the heavy lifting, while RLSP further improves market alignment."},{"finding":"Market‑driven self‑labeled sentiment data improves real‑world applicability of the model.","kind":"other","quote":"Market-driven labels (self‑labeled data) strongly improve real‑world applicability;"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":38,"citations":{"cited_by_in_corpus":78,"by_independent_authors":67,"how_cited":{"used_as_baseline":3,"uses_method_or_data":7,"extends":0,"discusses_findings":1,"mentions":49,"unclassified":18},"independent_papers":[{"paper":{"paper_id":"2403.00782","title":"Ploutos: Towards interpretable stock movement prediction with financial large language model","paper_date":"2024-02-18","authors":["Hanshuang Tong","Jun Li","Ning Wu","Ming Gong","Dongmei Zhang","Qi Zhang"],"empirical_rigor":8.5,"page_url":"https://thequant.space/flowcharts/ploutos-towards-interpretable-stock-movement-prediction-wit/"},"how":"used_as_baseline","quote":null},{"paper":{"paper_id":"2502.13165","title":"HedgeAgents: A Balanced-aware Multi-agent Financial Trading System","paper_date":"2025-02-17","authors":["Xiangyu Li","Yawen Zeng","Xiaofen Xing","Jin Xu","Xiangmin Xu"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/hedgeagents-a-balanced-aware-multi-agent-financial-trading/"},"how":"used_as_baseline","quote":null},{"paper":{"paper_id":"2602.07096","title":"RealFin: How Well Do LLMs Reason About Finance When Users Leave Things Unsaid?","paper_date":"2026-02-06","authors":["Yuyang Dai","Yan Lin","Zhuohan Xie","Yuxia Wang"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/realfin-how-well-do-llms-reason-about-finance-when-users-leave-things-unsaid/"},"how":"used_as_baseline","quote":null},{"paper":{"paper_id":"2502.18471","title":"FinBloom: Knowledge Grounding Large Language Model with Real-time Financial Data","paper_date":"2025-02-04","authors":["Ankur Sinha","Chaitanya Agarwal","Pekka Malo"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/finbloom-knowledge-grounding-large-language-model-with-real/"},"how":"discusses_findings","quote":"... are trained on publicly available financial text corpora, but are not competitive when evaluated on financial benchmarks"},{"paper":{"paper_id":"2402.03659","title":"Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models","paper_date":"2024-02-06","authors":["Kelvin J. L. Koa","Yunshan Ma","Ritchie Ng","Tat-Seng Chua"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/learning-to-generate-explainable-stock-predictions-using-sel/"},"how":"uses_method_or_data","quote":null},{"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":"2604.08649","title":"PRAGMA: Revolut Foundation Model","paper_date":"2026-04-09","authors":["Maxim Ostroukhov","Ruslan Mikhailov","Vladimir Iashin","Artem Sokolov","Andrei Akshonov","Vitaly Protasov"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/pragma-revolut-foundation-model/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2610.04040","title":"Agent Policy-Value Audit: Separating Transition Composition from Event Selection in Financial LLM Agents","paper_date":"2026-10-02","authors":["Mingyang","Chen","Yida","Xu","Huiwen","Chen"],"empirical_rigor":8,"page_url":"https://thequant.space/flowcharts/agent-policy-value-audit-separating-transition-composition-from-event-selection/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2603.17692","title":"Can Blindfolded LLMs Still Trade? An Anonymization-First Framework for Portfolio Optimization","paper_date":"2026-03-18","authors":["Joohyoung Jeon","Hongchul Lee"],"empirical_rigor":7.5,"page_url":"https://thequant.space/flowcharts/can-blindfolded-llms-still-trade-an-anonymization-first-framework-for-portfolio/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2603.19286","title":"Generalized Stock Price Prediction for Multiple Stocks Combined with News Fusion","paper_date":"2026-03-08","authors":["Pei-Jun Liao","Hung-Shin Lee","Yao-Fei Cheng","Li-Wei Chen","Hung-yi Lee","Hsin-Min Wang"],"empirical_rigor":6.5,"page_url":"https://thequant.space/flowcharts/generalized-stock-price-prediction-for-multiple-stocks-combined-with-news-fusion/"},"how":"uses_method_or_data","quote":null},{"paper":{"paper_id":"2601.03948","title":"Trade-R1: Bridging Verifiable Rewards to Stochastic Environments via Process-Level Reasoning Verification","paper_date":"2026-01-07","authors":["Rui Sun","Yifan Sun","Sheng Xu","Li Zhao","Jing Li","Daxin Jiang"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/trade-r1-bridging-verifiable-rewards-to-stochastic-environm/"},"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/AI4Finance-Foundation/FinGPT","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":"2026-11-14T16:28:11Z"},"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/"}