artpli/CodeIE
[ACL 23] CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors
This project explores how large language models, specifically those designed for code generation, can be used to extract structured information from unstructured text with minimal examples. It takes raw text and a few examples of the information you want to extract, and then outputs that information in a structured format. This is primarily a research tool for natural language processing researchers and engineers studying information extraction and large language models.
Use this if you are an NLP researcher interested in the capabilities of large code generation models for few-shot information extraction tasks.
Not ideal if you need a production-ready information extraction system or are not comfortable working with potentially deprecated OpenAI models.
Stars
40
Forks
1
Language
Python
License
—
Category
Last pushed
Dec 14, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/artpli/CodeIE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
mlabonne/llm-datasets
Curated list of datasets and tools for post-training.
malteos/llm-datasets
A collection of datasets for language model pretraining including scripts for downloading,...
magpie-align/magpie
[ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your...
jd-coderepos/llms4subjects
The official SemEval 2025 Task 5 - LLMs4Subjects - Shared Task Dataset repository
willxxy/ECG-Bench
A Unified Framework for Benchmarking Generative Electrocardiogram-Language Models (ELMs)