🎓Automatically Update agent Papers Daily using Github Actions (Update Every 12th hours)

Open replication of DeepSeek R1 for text-to-graph extraction.

Fully open reproduction of DeepSeek-R1

Resources for our paper: "Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training"

A reading list on LLM based Synthetic Data Generation 🔥

Real-time updated, fine-grained reading list on LLM-synthetic-data.🔥

Offical code implementation of paper "Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning" to appear in AAAI2025

Scalable toolkit for efficient model alignment

Companion code for FanOutQA: Multi-Hop, Multi-Document Question Answering for Large Language Models (ACL 2024)

Lightweight Armoury Crate alternative for Asus laptops and ROG Ally. Control tool for ROG Zephyrus G14, G15, G16, M16, Flow X13, Flow X16, TUF, Strix, Scar and other models

利用免费的大模型api来结合你的私域数据来生成sft训练数据（妥妥白嫖）支持llamafactory等工具的训练数据格式synthetic data

A simple, easy-to-hack GraphRAG implementation

Repository for "MultiHop-RAG: A Dataset for Evaluating Retrieval-Augmented Generation Across Documents" (COLM 2024)

Code implementation of synthetic continued pretraining

An open-source RAG-based tool for chatting with your documents.

A modular graph-based Retrieval-Augmented Generation (RAG) system

An open-source highly heterogeneous entity alignment (HHEA) toolkit.

FinRobot: An Open-Source AI Agent Platform for Financial Analysis using LLMs 🚀 🚀 🚀

Code and Data for the NAACL 24 paper: MacGyver: Are Large Language Models Creative Problem Solvers?

[KDD'2024] "HiGPT: Heterogenous Graph Language Models"

Hallucinations are often perceived as a significant limitation in current large language models (LLMs). However, is this always the case? Could these apparent errors harbor seeds of creativity? Thi…

Toward Practical Entity Alignment Method Design: Insights from New Highly Heterogeneous Knowledge Graph Datasets

A simple but effective method (and two new proposed datasets: ICEWS-WIKI, ICEWS-YAGO) for entity alignment on highly heterogeneous knowledge graphs.