Editing Language Model-Based Knowledge Graph Embeddings

Authors: Siyuan Cheng, Ningyu Zhang, Bozhong Tian, Xi Chen, Qingbin Liu, Huajun Chen

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We build four new datasets: E-FB15k237, A-FB15k237, E-WN18RR, and A-WN18RR, and evaluate several knowledge editing baselines demonstrating the limited ability of previous models to handle the proposed challenging task. We further propose a simple yet strong baseline dubbed KGEditor, which utilizes additional parametric layers of the hypernetwork to edit/add facts. Our comprehensive experimental results reveal that KGEditor excels in updating specific facts without impacting the overall performance, even when faced with limited training resources.
Researcher Affiliation Collaboration Siyuan Cheng1, 2, 4*, Ningyu Zhang1, 2 , Bozhong Tian1, 2*, Xi Chen4*, Qingbin Liu4, Huajun Chen1, 2, 3 1Zhejiang University 2Zhejiang University Ant Group Joint Laboratory of Knowledge Graph 3Donghai Laboratory 4Platform and Content Group, Tencent
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks (clearly labeled algorithm sections or code-like formatted procedures).
Open Source Code Yes Code and datasets will be available at https://github.com/Anonymous For Papers/Delta KG.
Open Datasets Yes We construct four datasets for EDIT and ADD tasks, based on two benchmarks FB15k-237 (Toutanova et al. 2015), and WN18RR (Dettmers et al. 2018). Code and datasets will be available at https://github.com/Anonymous For Papers/Delta KG.
Dataset Splits Yes Table 1: The statistics of datasets for the EDIT and ADD tasks. L-Test is the test set for knowledge locality to evaluate the rest of the knowledge in KGE.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names like Python 3.8, PyTorch 1.9, CPLEX 12.4) needed to replicate the experiment.
Experiment Setup No The paper does not contain specific experimental setup details (concrete hyperparameter values, training configurations, or system-level settings) in the main text.