KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction

arXiv:2403.07969v1 Announce Type: new
Abstract: In this paper, we propose KnowCoder, a Large Language Model (LLM) to conduct Universal Information Extraction (UIE) via code generation. KnowCoder aims to develop a kind of unified schema representation that LLMs can easily understand and an effective learning framework that encourages LLMs to follow schemas and extract structured knowledge accurately. To achieve these, KnowCoder introduces a code-style schema representation method to uniformly transform different schemas into Python classes, with which complex schema information, such …

abstract arxiv code code generation coding cs.ai cs.lg extraction framework information information extraction kind knowledge language language model large language large language model llm llms paper representation schema type universal via