{"paper_id":"2503.05185","title":"Towards Temporal-Aware Multi-Modal Retrieval Augmented Generation in Finance","authors":["Fengbin Zhu","Junfeng Li","Liangming Pan","Wenjie Wang","Fuli Feng","Chao Wang","Huanbo Luan","Tat-Seng Chua"],"paper_date":"2025-03-07","paper_type":"dataset-benchmark","paper_url":"https://arxiv.org/pdf/2503.05185v2","page_url":"https://thequant.space/flowcharts/towards-temporal-aware-multi-modal-retrieval-augmented-gener/","scores":{"empirical_rigor":8.5,"math_complexity":2.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes TMMHybridRAG, a novel temporal-aware multi-modal Retrieval-Augmented Generation method that integrates dense and graph retrieval techniques, and introduces the FinTMMBench benchmark.","quote":"we propose TMMHybridRAG, a novel temporal-aware multi-modal RAG method that integrates dense and graph retrieval techniques.","summary":"Finance decision-making often relies on in-depth data analysis across various data sources, including financial tables, news articles, stock prices, etc. In this work, we introduce FinTMMBench, the first comprehensive benchmark for evaluating temporal-aware multi-modal Retrieval-Augmented…","strategy":null},"assumptions":{"status":"none_found","items":[]},"datasets":{"status":"available","items":[{"name":"FinTMMBench","provider":"NASDAQ-100 companies","kind":"benchmark","access":"public","period":"2022","universe":"NASDAQ-100 companies","quote":"To construct FinTMMBench, we collect financial data of the NASDAQ-100 companies in 2022, which include four types as below."},{"name":"FinTMMBench raw data","provider":"NASDAQ-100 companies","kind":"benchmark","access":"public","period":null,"universe":"NASDAQ-100 companies","quote":"FinTMMBench consists of 34, 815 raw data entries from NASDAQ-100 companies across four modalities, including 1, 500 financial tables, 3, 133 news articles, 25, 200 daily stock price records, and 6, 267 visual technical charts."}],"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":"TMMHybridRAG (All) achieves the best results across all evaluation metrics, with EM 19.12%, F1 31.41%, accuracy 26.56%, and LLM-judge accuracy 21.53%.","kind":"performance","quote":"... it attains an EM score of 19.12%, an F1 score of 31.41, an accuracy of 26.56%, and an LLM-judge accuracy of 21.53%."},{"finding":"Despite being state-of-the-art, the F1 score remains relatively low at 31.41, highlighting substantial challenges in FinTMMBench.","kind":"negative","quote":"Though our TMMHybridRAG (All) achieves state-of-the-art on FinTMMBench, the F1 score remains relatively low at 31.41. This highlights the significant challenges inherent in FinTMMBench."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":13,"citations":{"cited_by_in_corpus":3,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":1,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":1},"independent_papers":[{"paper":{"paper_id":"2510.27334","title":"When AI Trading Agents Compete: Adverse Selection of Meta-Orders by Reinforcement Learning-Based Market Making","paper_date":"2025-10-31","authors":["Ali Raza Jafree","Konark Jain","Nick Firoozye"],"empirical_rigor":3,"page_url":"https://thequant.space/flowcharts/when-ai-trading-agents-compete-adverse-selection-of-meta-or/"},"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/lijunfeng99/FinTMMBench","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":"2026-11-14T17:42:57Z"},"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/"}