Characterizing Multimodal Long-form Summarization: A Case Study on Financial Reports

arXiv:2404.06162v1 Announce Type: cross
Abstract: As large language models (LLMs) expand the power of natural language processing to handle long inputs, rigorous and systematic analyses are necessary to understand their abilities and behavior. A salient application is summarization, due to its ubiquity and controversy (e.g., researchers have declared the death of summarization). In this paper, we use financial report summarization as a case study because financial reports not only are long but also use numbers and tables extensively. We propose …

abstract application arxiv behavior case case study controversy cs.ai cs.cl cs.lg death expand financial form inputs language language models language processing large language large language models llms multimodal natural natural language natural language processing power processing reports researchers study summarization type