Enabling and Analyzing How to Efficiently Extract Information from Hybrid Long Documents with LLMs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917606942834688 |
|---|---|
| author | Yue, Chongjian Xu, Xinrun Ma, Xiaojun Du, Lun Liu, Hengyu Ding, Zhiming Jiang, Yanbing Han, Shi Zhang, Dongmei |
| author_facet | Yue, Chongjian Xu, Xinrun Ma, Xiaojun Du, Lun Liu, Hengyu Ding, Zhiming Jiang, Yanbing Han, Shi Zhang, Dongmei |
| contents | Large Language Models (LLMs) demonstrate exceptional performance in textual understanding and tabular reasoning tasks. However, their ability to comprehend and analyze hybrid text, containing textual and tabular data, remains underexplored. In this research, we specialize in harnessing the potential of LLMs to comprehend critical information from financial reports, which are hybrid long-documents. We propose an Automated Financial Information Extraction (AFIE) framework that enhances LLMs' ability to comprehend and extract information from financial reports. To evaluate AFIE, we develop a Financial Reports Numerical Extraction (FINE) dataset and conduct an extensive experimental analysis. Our framework is effectively validated on GPT-3.5 and GPT-4, yielding average accuracy increases of 53.94% and 33.77%, respectively, compared to a naive method. These results suggest that the AFIE framework offers accuracy for automated numerical extraction from complex, hybrid documents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_16344 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Enabling and Analyzing How to Efficiently Extract Information from Hybrid Long Documents with LLMs Yue, Chongjian Xu, Xinrun Ma, Xiaojun Du, Lun Liu, Hengyu Ding, Zhiming Jiang, Yanbing Han, Shi Zhang, Dongmei Computation and Language Artificial Intelligence Large Language Models (LLMs) demonstrate exceptional performance in textual understanding and tabular reasoning tasks. However, their ability to comprehend and analyze hybrid text, containing textual and tabular data, remains underexplored. In this research, we specialize in harnessing the potential of LLMs to comprehend critical information from financial reports, which are hybrid long-documents. We propose an Automated Financial Information Extraction (AFIE) framework that enhances LLMs' ability to comprehend and extract information from financial reports. To evaluate AFIE, we develop a Financial Reports Numerical Extraction (FINE) dataset and conduct an extensive experimental analysis. Our framework is effectively validated on GPT-3.5 and GPT-4, yielding average accuracy increases of 53.94% and 33.77%, respectively, compared to a naive method. These results suggest that the AFIE framework offers accuracy for automated numerical extraction from complex, hybrid documents. |
| title | Enabling and Analyzing How to Efficiently Extract Information from Hybrid Long Documents with LLMs |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2305.16344 |