MinPrompt: Graph-based Minimal Prompt Data Augmentation for Few-shot Question Answering

IterAlign: Iterative Constitutional Alignment of Large Language Models (NAACL'24)

Code for the working paper "Planning with Diffusion for Professional Basketball Behavior Synthesis"

This is the code for our paper "BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers".

The official Meta Llama 3 GitHub site

Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs (ACL 2024)

Examples and guides for using the GLM APIs

A Deep Learning Python Toolkit for Healthcare Applications.

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery

The source code used for paper "PIEClass: Weakly-Supervised Text Classification with Prompting and Noise-Robust Iterative Ensemble Training", published in EMNLP 2023.

HetSeq: Distributed GPU Training on Heterogeneous Infrastructure

Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding (Findings of EMNLP'23)

[SIGIR 2023] This is the code for our short paper `Weakly-Supervised Scientific Document Classification via Retrieval-Augmented Multi-Stage Training'.

The raw data and analysis code for the Microsoft Academic paper recommender system user study conducted in 2018.

Weakly Supervised Multi-Label Classification of Full-Text Scientific Papers (KDD'23)

A curated list of papers and resources based on "Large Language Models on Graphs: A Comprehensive Survey".

The first open Federated Learning framework implemented in C++ and Python.

Heterformer: Transformer-based Deep Node Representation Learning on Heterogeneous Text-Rich Networks (KDD 2023)

[ICML 2023] Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning

Corpus of auto-labeled text for the cyber security domain

Patton: Language Model Pretraining on Text-rich Networks (ACL 2023 main oral)

Document Similarity for Texts of Varying Lengths via Hidden Topics

Inference code for Llama models

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

Reviewer-paper matching for ACL

Code for the paper "Open Domain Question Answering with A Unified Knowledge Interface" (ACL 2022)