{"paper_id":"2509.08742","title":"FinZero: Launching Multi-modal Financial Time Series Forecast with Large Reasoning Model","authors":["Yanlong Wang","Jian Xu","Fei Ma","Hongkang Zhang","Hang Yu","Tiantian Gao","Yu Wang","Haochen You","Shao-Lun Huang","Danny Dongning Sun","Xiao-Ping Zhang"],"paper_date":"2025-09-10","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2509.08742v1","page_url":"https://thequant.space/flowcharts/finzero-launching-multi-modal-financial-time-series-forecas/","scores":{"empirical_rigor":7,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a multimodal financial time‑series model called FinZero, a new financial image‑text dataset (FVLDB), and the Uncertainty‑adjusted Group Relative Policy Optimization (UARPO) fine‑tuning method.","quote":"We first construct a diverse financial image-text dataset (FVLDB) and develop the Uncertainty-adjusted Group Relative Policy Optimization (UARPO) method to enable the model not only output predictions but also analyze the uncertainty of those predictions. We then proposed FinZero, a multimodal pre-trained model finetun","summary":"Financial time series forecasting is both highly significant and challenging. Previous approaches typically standardized time series data before feeding it into forecasting models, but this encoding process inherently leads to a loss of important information. Moreover, past time series models…","strategy":null},"assumptions":{"status":"none_found","items":[]},"datasets":{"status":"available","items":[{"name":"FVLDB","provider":null,"kind":"other","access":"unknown","period":null,"universe":null,"quote":"To support this, we construct the FVLDB dataset, comprising over 10,000 financial time series image-text pairs."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"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":"forecast-accuracy","findings":[{"finding":"FinZero improves prediction accuracy in the high‑confidence group by about 13.5% relative to GPT‑4o.","kind":"predictive-accuracy","quote":"FinZero achieves an approximate 13.48% improvement in prediction accuracy over GPT‑4o in the high‑confidence group, demonstrating the effectiveness of reinforcement learning fine‑tuning in multimodal large model."},{"finding":"FinZero attains the highest accuracy across confidence score groups, with 62.13% in the high‑confidence group versus 49.85% for GPT‑4o.","kind":"performance","quote":"... increased by approximately 13.5% relative to that of GPT‑4o."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":40,"citations":{"cited_by_in_corpus":1,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"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":"2026-11-14T16:37:51Z"},"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/"}