LAPDoc: Layout-Aware Prompting for Documents

arXiv:2402.09841v1 Announce Type: cross
Abstract: Recent advances in training large language models (LLMs) using massive amounts of solely textual data lead to strong generalization across many domains and tasks, including document-specific tasks. Opposed to that there is a trend to train multi-modal transformer architectures tailored for document understanding that are designed specifically to fuse textual inputs with the corresponding document layout. This involves a separate fine-tuning step for which additional training data is required. At present, no document transformers with …

abstract advances architectures arxiv cs.cl cs.lg data document documents document understanding domains language language models large language large language models llms massive modal multi-modal prompting specific tasks tasks textual train training transformer trend type understanding