{"paper_id":"2408.11878","title":"Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications","authors":["Jimin Huang","Mengxi Xiao","Dong Li","Zihao Jiang","Yuzhe Yang","Yifei Zhang","Lingfei Qian","Yan Wang","Xueqing Peng","Yang Ren","Ruoyu Xiang","Zhengyu Chen","Xiao Zhang","Yueru He","Weiguang Han","Shunian Chen","Lihang Shen","Daniel Kim","Yangyang Yu","Yupeng Cao","Zhiyang Deng","Haohang Li","Duanyu Feng","Yongfu Dai","VijayaSai Somasundaram","Peng Lu","Guojun Xiong","Zhiwei Liu","Zheheng Luo","Zhiyuan Yao","Ruey-Ling Weng","Meikang Qiu","Kaleb E Smith","Honghai Yu","Yanzhao Lai","Min Peng","Jian-Yun Nie","Jordan W. Suchow","Xiao-Yang Liu","Benyou Wang","Alejandro Lopez-Lira","Qianqian Xie","Sophia Ananiadou","Junichi Tsujii"],"paper_date":"2024-08-20","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2408.11878v3","page_url":"https://thequant.space/flowcharts/open-finllms-open-multimodal-large-language-models-for-fina/","scores":{"empirical_rigor":8.5,"math_complexity":4,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes Open-FinLLMs, an open-source suite of multimodal financial large language models covering text, tabular, time-series, and chart data.","quote":"Open-FinLLMs, the first open-source multimodal financial LLMs designed to handle diverse tasks across text, tabular, time-series, and chart data","summary":"Financial LLMs hold promise for advancing financial tasks and domain-specific applications. However, they are limited by scarce corpora, weak multimodal capabilities, and narrow evaluations, making them less suited for real-world application. To address this, we introduce \\textit{“Open-FinLLMs”}…","strategy":"FinLLaMA"},"assumptions":{"status":"none_found","items":[]},"datasets":{"status":"available","items":[{"name":"Yahoo Finance data","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":null,"universe":null,"quote":"The data is sourced from Yahoo Finance, offering a robust foundation for time-series analysis and predictive modeling.","known_id":"yahoo-finance"},{"name":"SEC Filings","provider":"U.S. Securities and Exchange Commission (EDGAR)","kind":"fundamentals","access":"public","period":"1994-2020","universe":null,"quote":"SEC Filings: This section includes 6 billion tokens from U.S. SEC filings, such as 10-K and 10-Q reports, spanning from 1994 to 2020.","known_id":"edgar"}],"known":[{"id":"edgar","name":"SEC EDGAR","provider":"U.S. Securities and Exchange Commission","kind":"text-news","access":"public","quote":"Data: We evaluated the model’s performance on the Decision Making task using the following datasets: • OHLCV data: Open-High-Low-Close prices and trading volume data for COIN, GOOG, NIO, and TSLA, obtained from Yahoo Fi-nance. • News data: Collected from Alpaca News API for COIN, GOOG, NIO, and TSLA. • Form 10-Q data: Extracted from SEC EDGAR for COIN, GOOG, and TSLA. • Form 10-K data: Retrieved from SEC EDGAR for CO","mentions":3,"used_in":3},{"id":"fiqa","name":"FiQA","provider":"FiQA challenge","kind":"benchmark","access":"public","quote":"E.4.2 Descriptions of Few-shot Evaluation Tasks In our few-shot evaluations, we use three financial NLP tasks: • Sentiment Analysis: Extracting sentiment in-formation from financial texts using the FPB and FiQA-SA datasets, which focus on deter-mining sentiment polarity (positive, negative, or neutral) in financial sentences. • Classification: Evaluating the model’s capa-bility to classify financial texts.","mentions":7,"used_in":1},{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"The data is sourced from Yahoo Finance, offering a robust foundation for time-series analysis and predictive modeling. • SEC Filings: This section includes 6 billion tokens from U.S. SEC filings, such as 10-K and 10-Q reports, spanning from 1994 to 2020.","mentions":1,"used_in":1}],"sample":{"start":"2021-08","end":"2023-04","market":"single-asset trading dataset (TSLA, COIN, GOOG, NIO)","asset_class":"multi-asset","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":false,"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":"FinLLaMA achieves an NER F1 score of 82.10, far surpassing LLaMA3-8B (39.18) and BloombergGPT (60.82).","kind":"performance","quote":"In the NER task, FinLLaMA achieves a remarkable F1 score of 82.10, significantly surpassing its backbone model LLaMA3-8B (39.18), LLaMA3.1-8B (49.04), and BloombergGPT (60.82)."},{"finding":"FinLLaMA attains 85.54 accuracy on the Headlines classification dataset, outperforming LLaMA3-8B (80.59) and BloombergGPT (82.20).","kind":"performance","quote":"In the Headlines dataset for classification, FinLLaMA achieves a score of 85.54, outperforming LLaMA3-8B (80.59), LLaMA3.1-8B (59.95), and BloombergGPT (82.20)."}],"reported_performance":{"strategy":"FinLLaMA","sharpe":1.4088,"sharpe_benchmark":-0.3823,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":26.93},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":18,"citations":{"cited_by_in_corpus":10,"by_independent_authors":5,"how_cited":{"used_as_baseline":0,"uses_method_or_data":1,"extends":0,"discusses_findings":0,"mentions":4,"unclassified":5},"independent_papers":[{"paper":{"paper_id":"2506.04290","title":"Interpretable LLMs for Credit Risk: A Systematic Review and Taxonomy","paper_date":"2025-06-04","authors":["Muhammed Golec","Maha AlabdulJalil"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/interpretable-llms-for-credit-risk-a-systematic-review-and-taxonomy/"},"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://huggingface.co/collections/TheFinAI/open-finllms-finllama-finllama-instruct-finllava","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":"2026-11-14T18:03:39Z"},"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/"}