Paper Reading AI Learner

Knowledge Graph Enhanced Large Language Model Editing

2024-02-21 07:52:26
Mengqi Zhang, Xiaotian Ye, Qiang Liu, Pengjie Ren, Shu Wu, Zhumin Chen

Abstract

Large language models (LLMs) are pivotal in advancing natural language processing (NLP) tasks, yet their efficacy is hampered by inaccuracies and outdated knowledge. Model editing emerges as a promising solution to address these challenges. However, existing editing methods struggle to track and incorporate changes in knowledge associated with edits, which limits the generalization ability of postedit LLMs in processing edited knowledge. To tackle these problems, we propose a novel model editing method that leverages knowledge graphs for enhancing LLM editing, namely GLAME. Specifically, we first utilize a knowledge graph augmentation module to uncover associated knowledge that has changed due to editing, obtaining its internal representations within LLMs. This approach allows knowledge alterations within LLMs to be reflected through an external graph structure. Subsequently, we design a graph-based knowledge edit module to integrate structured knowledge into the model editing. This ensures that the updated parameters reflect not only the modifications of the edited knowledge but also the changes in other associated knowledge resulting from the editing process. Comprehensive experiments conducted on GPT-J and GPT-2 XL demonstrate that GLAME significantly improves the generalization capabilities of post-edit LLMs in employing edited knowledge.

Abstract (translated)

大语言模型(LLMs)在推动自然语言处理(NLP)任务方面具有关键作用,然而其有效性受到不准确和过时知识的限制。模型编辑成为解决这些挑战的有前景的解决方案。然而,现有的编辑方法很难跟踪和包含编辑过程中知识相关的变化,这限制了发布经过修改的LLM在处理编辑知识时的泛化能力。为了应对这些问题,我们提出了一个新模型编辑方法,即GLAME。具体来说,我们首先利用知识图谱增强模块发现由于编辑而发生变化的相关知识,并在LLMs的内部表示中获取其内部表示。这种方法允许LLM中知识的变化通过外部图结构反映出来。接着,我们设计了一个基于图的知识编辑模块,将结构化知识集成到模型编辑中。这确保了更新参数不仅反映了编辑知识的变化,还反映了编辑过程中产生的其他相关知识的变化。对GPT-J和GPT-2 XL的全面实验证明,GLAME显著提高了用于应用编辑知识的LLM的泛化能力。

URL

https://arxiv.org/abs/2402.13593

PDF

https://arxiv.org/pdf/2402.13593.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot