paper-with-me

홈 › Papers

UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction

2024-02-10 · Yansong Ning, Hao liu

Urban knowledge graph has recently worked as an emerging building block to distill critical knowledge from multi-sourced urban data for diverse urban application scenarios. Despite its promising benefits, urban knowledge graph construction (UrbanKGC) still heavily relies on manual effort, hindering its potential advancement. This paper presents UrbanKGent, a unified large language model agent framework, for urban knowledge graph construction. Specifically, we first construct the knowledgeable instruction set for UrbanKGC tasks (such as relational triplet extraction and knowledge graph completion) via heterogeneity-aware and geospatial-infused instruction generation. Moreover, we propose a tool-augmented iterative trajectory refinement module to enhance and refine the trajectories distilled from GPT-4. Through hybrid instruction fine-tuning with augmented trajectories on Llama 2 and Llama 3 family, we obtain UrbanKGC agent family, consisting of UrbanKGent-7/8/13B version. We perform a comprehensive evaluation on two real-world datasets using both human and GPT-4 self-evaluation. The experimental results demonstrate that UrbanKGent family can not only significantly outperform 31 baselines in UrbanKGC tasks, but also surpass the state-of-the-art LLM, GPT-4, by more than 10% with approximately 20 times lower cost. Compared with the existing benchmark, the UrbanKGent family could help construct an UrbanKG with hundreds of times richer relationships using only one-fifth of the data. Our data and code are available at https://github.com/usail-hkust/UrbanKGent.

📄 PDF Abstract BibTeX arXiv:2402.06861

Code (1)

usail-hkust/urbankgent 공식 구현 pytorch

Tasks

graph constructionKnowledge Graph CompletionLanguage ModelingLanguage ModellingLarge Language ModelTriplet

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
LLaMA LLaMA is a collection of foundation language models ranging from 7B to 65B parameters. It is based on the transformer architecture with various improvements that were…
Position-Wise Feed-Forward Layer 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

TrajAgent: An Agent Framework for Unified Trajectory Modelling

2024-10-27 · Yuwei Du, Jie Feng, Jie Zhao, Yong Li

Trajectory modeling, which includes research on trajectory data pattern mining and future prediction, has widespread applications in areas such as life services, urban transportation, and public administration. Numerous …

Future predictionLanguage ModelingLanguage ModellingLarge Language Model+1

Agent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation Systems

2025-05-28 · Hoang Pham, Thuy-Duong Nguyen, Khac-Hoai Nam Bui

This paper presents a novel approach for unified retrieval-augmented generation (RAG) systems using the recent emerging large language model (LLM) agent concept. Specifically, Agent LLM, which utilizes LLM as fundamental…

Large Language ModelQuestion AnsweringRAGRetrieval+1

Language-Guided Multi-Agent Learning in Simulations: A Unified Framework and Evaluation

2025-06-01 · Zhengyang Li

This paper introduces LLM-MARL, a unified framework that incorporates large language models (LLMs) into multi-agent reinforcement learning (MARL) to enhance coordination, communication, and generalization in simulated ga…

Language ModelingLanguage ModellingMulti-agent Reinforcement LearningStarcraft+2

Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents

2026-01-05 · Yi Yu, Liuyi Yao, Yuexiang Xie, Qingquan Tan 외 arxiv

Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows, making effective memory management critical. Existing methods typically handle long-term memory (LTM…

Reinforcement Learning

MemEngine: A Unified and Modular Library for Developing Advanced Memory of LLM-based Agents

2025-05-04 · Zeyu Zhang, Quanyu Dai, Xu Chen, Rui Li 외

Recently, large language model based (LLM-based) agents have been widely applied across various fields. As a critical part, their memory capabilities have captured significant interest from both industrial and academic c…

Language ModelingLanguage ModellingLarge Language Model