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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Fengbin, Li, Junfeng, Pan, Liangming, Wang, Wenjie, Feng, Fuli, Wang, Chao, Luan, Huanbo, Chua, Tat-Seng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911087692087296
author Zhu, Fengbin
Li, Junfeng
Pan, Liangming
Wang, Wenjie
Feng, Fuli
Wang, Chao
Luan, Huanbo
Chua, Tat-Seng
author_facet Zhu, Fengbin
Li, Junfeng
Pan, Liangming
Wang, Wenjie
Feng, Fuli
Wang, Chao
Luan, Huanbo
Chua, Tat-Seng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_05185
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Temporal-Aware Multi-Modal Retrieval Augmented Generation in Finance
Zhu, Fengbin
Li, Junfeng
Pan, Liangming
Wang, Wenjie
Feng, Fuli
Wang, Chao
Luan, Huanbo
Chua, Tat-Seng
Computational Finance
Artificial Intelligence
Multimedia
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.
title Towards Temporal-Aware Multi-Modal Retrieval Augmented Generation in Finance
topic Computational Finance
Artificial Intelligence
Multimedia
url https://arxiv.org/abs/2503.05185