Enabling and Analyzing How to Efficiently Extract Information from Hybrid Long Documents with LLMs

arXiv:2305.16344v2 Announce Type: replace
Abstract: 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 …

abstract analyze arxiv cs.ai cs.cl data documents enabling extract however hybrid information language language models large language large language models llms performance reasoning research tabular tabular data tasks text textual type understanding