# KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction

arXiv: https://arxiv.org/abs/2403.07969 · HTML: https://mlsanity.com/paper/2403.07969/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 51 references that are in the map.
- First posted on arXiv 12 Mar 2024.

## Builds on (most cited first, 21 of 21)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction](https://mlsanity.com/paper/1808.09602/) (2018)
- [Unified Structure Generation for Universal Information Extraction](https://mlsanity.com/paper/2203.12277/) (2022)
- [Large Language Models for Generative Information Extraction: A Survey](https://mlsanity.com/paper/2312.17617/) (2023)
- [InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction](https://mlsanity.com/paper/2304.08085/) (2023)
- [Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction](https://mlsanity.com/paper/2106.09232/) (2021)
- [GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction](https://mlsanity.com/paper/2310.03668/) (2023)
- [CrossNER: Evaluating Cross-Domain Named Entity Recognition](https://mlsanity.com/paper/2012.04373/) (2020)
- [CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors](https://mlsanity.com/paper/2305.05711/) (2023)
- [SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations Between Pairs of Nominals](https://mlsanity.com/paper/1911.10422/) (2019)
- [Universal Information Extraction as Unified Semantic Matching](https://mlsanity.com/paper/2301.03282/) (2023)
- [Relation Classification via Recurrent Neural Network](https://mlsanity.com/paper/1508.01006/) (2015)
- [DeepStruct: Pretraining of Language Models for Structure Prediction](https://mlsanity.com/paper/2205.10475/) (2022)
- [Retrieval-Augmented Code Generation for Universal Information Extraction](https://mlsanity.com/paper/2311.02962/) (2023)
- [Improving Distantly Supervised Relation Extraction using Word and Entity Based Attention](https://mlsanity.com/paper/1804.06987/) (2018)
- [Biomedical Named Entity Recognition at Scale](https://mlsanity.com/paper/2011.06315/) (2020)
- [GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling](https://mlsanity.com/paper/1906.02437/) (2019)

## Built on by (most cited first, 30 of 34)

- [Instruction-Tuning LLMs for Event Extraction with Annotation Guidelines](https://mlsanity.com/paper/2502.16377/) (2025)
- [CodeTaxo: Enhancing Taxonomy Expansion with Limited Examples via Code Language Prompts](https://mlsanity.com/paper/2408.09070/) (2024)
- [Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models](https://mlsanity.com/paper/2411.03884/) (2024)
- [A Survey on Large Language Models in Multimodal Recommender Systems](https://mlsanity.com/paper/2505.09777/) (2025)
- [Revisiting Prompt Optimization with Large Reasoning Models-A Case Study on Event Extraction](https://mlsanity.com/paper/2504.07357/) (2025)
- [Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity Recognition](https://mlsanity.com/paper/2406.11192/) (2024)
- [Event Extraction in Large Language Model](https://mlsanity.com/paper/2512.19537/) (2025)
- [Retrieval Augmented Instruction Tuning for Open NER with Large Language Models](https://mlsanity.com/paper/2406.17305/) (2024)
- [GuideX: Guided Synthetic Data Generation for Zero-Shot Information Extraction](https://mlsanity.com/paper/2506.00649/) (2025)
- [RUIE: Retrieval-based Unified Information Extraction using Large Language Model](https://mlsanity.com/paper/2409.11673/) (2024)
- [KnowCoder-X: Boosting Multilingual Information Extraction via Code](https://mlsanity.com/paper/2411.04794/) (2024)
- [Scale-Distribution Decoupling: Enabling Stable and Effective Training of Large Language Models](https://mlsanity.com/paper/2502.15499/) (2025)
- [Schema as Parameterized Tools for Universal Information Extraction](https://mlsanity.com/paper/2506.01276/) (2025)
- [Selecting and Merging: Towards Adaptable and Scalable Named Entity Recognition with Large Language Models](https://mlsanity.com/paper/2506.22813/) (2025)
- [PrivComp-KG : Leveraging Knowledge Graph and Large Language Models for Privacy Policy Compliance Verification](https://mlsanity.com/paper/2404.19744/) (2024)
- [Towards Event Extraction with Massive Types: LLM-based Collaborative Annotation and Partitioning Extraction](https://mlsanity.com/paper/2503.02628/) (2025)
- [MPL: Multiple Programming Languages with Large Language Models for Information Extraction](https://mlsanity.com/paper/2505.16107/) (2025)
- [A System for Name and Address Parsing with Large Language Models](https://mlsanity.com/paper/2601.18014/) (2026)
- [EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific Domain](https://mlsanity.com/paper/2406.14075/) (2024)
- [Label Drop for Multi-Aspect Relation Modeling in Universal Information Extraction](https://mlsanity.com/paper/2502.12614/) (2025)
- [Towards Robust Universal Information Extraction: Benchmark, Evaluation, and Solution](https://mlsanity.com/paper/2503.03201/) (2025)
- [KnowCoder-V2: Deep Knowledge Analysis](https://mlsanity.com/paper/2506.06881/) (2025)
- [A Semantic Parsing Framework for End-to-End Time Normalization](https://mlsanity.com/paper/2507.06450/) (2025)
- [Towards Knowledgeable Deep Research: Framework and Benchmark](https://mlsanity.com/paper/2604.07720/) (2026)
- [Enhancing Biomedical Named Entity Recognition via Multiple Programming Languages Instruction Tuning and Ensemble Method](https://mlsanity.com/paper/2610.02949/) (2026)
- [Evaluation of LLM-based Strategies for the Extraction of Food Product Information from Online Shops](https://mlsanity.com/paper/2506.21585/) (2025)
- [MME-RAG: Multi-Manager-Expert Retrieval-Augmented Generation for Fine-Grained Entity Recognition in Task-Oriented Dialogues](https://mlsanity.com/paper/2511.12213/) (2025)
- [Knots: A Large-Scale Multi-Agent Enhanced Expert-Annotated Dataset and LLM Prompt Optimization for NOTAM Semantic Parsing](https://mlsanity.com/paper/2511.12630/) (2025)
- [Code-MIE: A Code-style Model for Multimodal Information Extraction with Scene Graph and Entity Attribute Knowledge Enhancement](https://mlsanity.com/paper/2603.20781/) (2026)
- [ProUIE: A Macro-to-Micro Progressive Learning Method for LLM-based Universal Information Extraction](https://mlsanity.com/paper/2604.10633/) (2026)

## Abstract (arXiv)

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 as constraints among tasks in UIE, can be captured in an LLM-friendly manner. We further construct a code-style schema library covering over 30,000 types of knowledge, which is the largest one for UIE, to the best of our knowledge. To ease the learning process of LLMs, KnowCoder contains a two-phase learning framework that enhances its schema understanding ability via code pretraining and its schema following ability via instruction tuning. After code pretraining on around 1.5B automatically constructed data, KnowCoder already attains remarkable generalization ability and achieves relative improvements by 49.8% F1, compared to LLaMA2, under the few-shot setting. After instruction tuning, KnowCoder further exhibits strong generalization ability on unseen schemas and achieves up to 12.5% and 21.9%, compared to sota baselines, under the zero-shot setting and the low resource setting, respectively. Additionally, based on our unified schema representations, various human-annotated datasets can simultaneously be utilized to refine KnowCoder, which achieves significant improvements up to 7.5% under the supervised setting.