Projects sharing features with PGIM

unikg

This is the github repository for the paper to be appeared at NAACL 2024 main conference: Self-Improving for Zero-Shot Named Entity Recognition with Large Language Models.

This repo contains the code and datasets for paper "ProgGen: Generating Named Entity Recognition Datasets Step-by-step with Self-Reflexive Large Language Models".

If you are just looking to download the LoRA weights directly, use this url: https://figshare.com/ndownloader/files/43044994 and view the data entry on Figshare.

This repository contains code to run the inference and evaluation of NER as described in our NAACL 2024 paper: On-the-fly Definition Augmentation of LLMs for Biomedical NER

This project is the codebase used for our weak supervision experiments using E3C dataset annotated with InstructGPT-3 and dictionary.

Dependencies are managed using Poetry. Use poetry install to install dependencies. You can then use poetry shell to obtain a shell with the created virtual environment activated.

CHisIEC: An Information Extraction Corpus for Ancient Chinese History

Flair is a natural language processing framework for training and applying models for sequence labeling and text classification. It provides a system for generating word embeddings and identifying semantic entities within text. The framework includes a dedicated system for zero and few-shot learning, enabling text classification and entity extraction using minimal training examples by leveraging pre-trained knowledge. Its capabilities cover named entity recognition, sentiment analysis, and the training of specialized models using custom datasets. It also includes tooling for the visual highl

Flair is a transformer-based natural language processing framework used to build and train models for text classification and sequence tagging. It provides a specialized library for generating contextual text embeddings and performing linguistic analysis. The framework includes dedicated tools for named entity recognition, including the identification of specialized biomedical entities across multiple languages. It further supports entity linking to map identified text mentions to unique entries within general or biomedical knowledge bases. The project covers a broad range of language analys

llmware is a Python framework for AI agent orchestration and model management, designed to coordinate multi-model workflows and autonomous agents. It provides a unified model catalog and standardized interface to execute specialized language models for complex research, analysis, and structured data generation. The project distinguishes itself through its heavy emphasis on local execution and quantized inference, allowing models to run on private infrastructure using CPU, GPU, and NPU acceleration via runtimes like ONNX and OpenVino. It features a specialized ability to translate natural lang

Source code and data for ACL 2023 main conference paper DICE: Data-Efficient Clinical Event Extraction with Generative Models.

Langchain-Chatchat is a system for building retrieval-augmented generation applications and autonomous AI agents. It integrates a knowledge base management system and an agent framework to enable language models to interact with private documents and execute multi-step tasks through external tools. The platform supports local deployment of language models on private infrastructure to operate without an internet connection. It includes a multimodal AI platform that combines vision models for image analysis with text-to-image generation capabilities. The system provides a web-based conversatio

Code and ressources for evaluating Named Entity Recognition using Few-Shot Prompting with Large Language Models

The code for EMNLP24 paper "Double-Checker: Large Language Model as a Checker for Few-shot Named Entity Recognition"

Project Overview:

全局指针统一处理嵌套与非嵌套NER。

Ragas is an evaluation framework and performance benchmark designed to quantify the quality of retrieval augmented generation pipelines. It functions as an application optimizer to identify bottlenecks in language model workflows using automated metrics and model-based scoring. The framework includes a system for generating synthetic datasets that mimic production scenarios and edge cases to create realistic test cases. It enables reference-free assessment, allowing the evaluation of response quality by analyzing grounding in the provided context without requiring gold-standard labels. The s

CollabKG is an open-source IE annotation toolkit that unifies NER, RE, and EE tasks, integrates KG and EKG, and supports both English and Chinese languages. - CollabKG combines automatic and manual labeling to build a learnable human-machine cooperative system. In particular, humans benefit from…

We provide an implementation of GCD that is compatible with the popular Transformers library!

nano-graphrag is a retrieval system that uses knowledge graphs to provide structured context for large language model responses. It functions as a knowledge graph indexer that transforms unstructured text into a network of entities and relationships, as well as a hybrid graph retrieval system. The project differentiates itself by combining local neighborhood searches with global community summaries to answer complex natural language questions. It includes a knowledge graph visualizer that generates HTML representations of entities and their relationships to map indexed knowledge. The framewo

LightRAG is a graph-based retrieval framework designed to build retrieval-augmented generation pipelines. It structures unstructured text into knowledge graphs, enabling multi-hop reasoning and complex query synthesis across large document collections. By integrating dense vector embeddings with structured knowledge graphs, the system facilitates both similarity-based and relationship-aware information retrieval. The framework distinguishes itself through a dual-level retrieval strategy that combines low-level keyword matching with high-level semantic graph traversal to capture both specific

ACL2026 "MiniRAG: Making RAG Simpler with Small and Open-Sourced Language Models"

RAG-Anything is a retrieval-augmented generation framework designed to index diverse document formats and perform semantic search using local machine learning models. It functions as a local multimodal data processor, extracting and organizing information from various file types into a unified knowledge base to facilitate private document analysis. The system distinguishes itself through its high-throughput ingestion engine, which processes large batches of documents into searchable vector embeddings. By executing machine learning models directly on local hardware, the framework ensures that

DB-GPT is an agentic data analysis platform and business intelligence AI that functions as a large language model data assistant. It provides a text-to-SQL interface and a sandboxed code execution environment to translate natural language into executable database queries and Python scripts. The platform utilizes iterative agentic reasoning to plan and execute multi-step data analysis workflows through tool calls. It features a modular skill-based extension system that allows domain knowledge and analysis workflows to be packaged into reusable functional components. The system integrates data