mlsanityData to 14 Oct 2026

Towards Temporal-Aware Multi-Modal Retrieval Augmented Generation in Finance

arXiv 2503.05185 ↗First posted 7 Mar 2025q-fin.CP cs.AI cs.MMcited by 8

On the map: Retrieval-augmented generation → Legal and financial RAG

Abstract (arXiv)

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 Generation (RAG) systems in finance. Built from heterologous data of NASDAQ 100 companies, FinTMMBench offers three significant advantages. 1) Multi-modal Corpus: It encompasses a hybrid of financial tables, news articles, daily stock prices, and visual technical charts as the corpus. 2) Temporal-aware Questions: Each question requires the retrieval and interpretation of its relevant data over a specific time period, including daily, weekly, monthly, quarterly, and annual periods. 3) Diverse Financial Analysis Tasks: The questions involve 10 different financial analysis tasks designed by domain experts, including information extraction, trend analysis, sentiment analysis and event detection, etc. We further propose a novel TMMHybridRAG method, which first leverages LLMs to convert data from other modalities (e.g., tabular, visual and time-series data) into textual format and then incorporates temporal information in each node when constructing graphs and dense indexes. Its effectiveness has been validated in extensive experiments, but notable gaps remain, highlighting the challenges presented by our FinTMMBench.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in Legal and financial RAG, one of 15 directions in Retrieval-augmented generation. Builds on 16 of its 33 references that are in the map. First posted on arXiv 7 Mar 2025.

Builds on

16 of 33 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain17 Dec
  2. 2024HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction9 Aug
  3. 2024AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Framework19 Mar

Other references · 13

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  3. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  4. 2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 562
  5. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 408
  6. 2013Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Textscited by 310
  7. 2023FinanceBench: A New Benchmark for Financial Question Answeringcited by 270
  8. 2021MultiModalQA: Complex Question Answering over Text, Tables and Imagescited by 179
  9. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  10. 2022MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Datacited by 121
  11. 2022Towards Complex Document Understanding By Discrete Reasoningcited by 82
  12. 2024VISTA: Visualized Text Embedding For Universal Multi-Modal Retrievalcited by 67
1 more
  1. 2024FinTextQA: A Dataset for Long-form Financial Question Answeringcited by 54

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 4.

8 papers.

  1. 2025Reading Between the Timelines: RAG for Answering Diachronic Questionscited by 4
  2. 2026FinMTM: A Multi-Turn Multimodal Benchmark for Financial Reasoning and Agent Evaluationcited by 4
  3. 2026Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memorycited by 4
  4. 2025T2-RAGBench: Text-and-Table Benchmark for Evaluating Retrieval-Augmented Generationcited by 3
  5. 2025Multimedia and Visual Analytics in the Agentic Eracited by 1
  6. 2026Strat-LLM: Stratified Strategy Alignment for LLM-based Stock Trading with Real-time Multi-Source Signalscited by 1
  7. 2025History Rhymes: Macro-Contextual Retrieval for Robust Financial Forecastingcited by 0
  8. 2026Frontier Financial Judgement: Can agents tell what might move a stock?cited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering
  2. 2025Optimizing Retrieval Strategies for Financial Question Answering Documents in Retrieval-Augmented Generation Systems
  3. 2025MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering
  4. 2025Retrieval-augmented Large Language Models for Financial Time Series Forecasting
  5. 2025Metadata-Driven Retrieval-Augmented Generation for Financial Question Answering
  6. 2025FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domain
  7. 2025FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation
  8. 2024Multi-Reranker: Maximizing performance of retrieval-augmented generation in the FinanceRAG challenge