StructLM: Towards Building Generalist Models for Structured Knowledge Grounding

arXiv:2402.16671v1 Announce Type: new
Abstract: Structured data sources, such as tables, graphs, and databases, are ubiquitous knowledge sources. Despite the demonstrated capabilities of large language models (LLMs) on plain text, their proficiency in interpreting and utilizing structured data remains limited. Our investigation reveals a notable deficiency in LLMs' ability to process structured data, e.g., ChatGPT lags behind state-of-the-art (SoTA) model by an average of 35%. To augment the Structured Knowledge Grounding (SKG) capabilities in LLMs, we have developed a comprehensive …

abstract arxiv building capabilities cs.cl data databases data sources graphs investigation knowledge language language models large language large language models llms process structured data tables text type