# Multi-perspective Improvement of Knowledge Graph Completion with Large Language Models

arXiv: https://arxiv.org/abs/2403.01972 · HTML: https://mlsanity.com/paper/2403.01972/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 37 references that are in the map.
- First posted on arXiv 4 Mar 2024.

## Builds on (most cited first, 16 of 16)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [GLM-130B: An Open Bilingual Pre-trained Model](https://mlsanity.com/paper/2210.02414/) (2022)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation](https://mlsanity.com/paper/1911.06136/) (2019)
- [KG-BERT: BERT for Knowledge Graph Completion](https://mlsanity.com/paper/1909.03193/) (2019)
- [Low-Dimensional Hyperbolic Knowledge Graph Embeddings](https://mlsanity.com/paper/2005.00545/) (2020)
- [Large Language Models for Generative Information Extraction: A Survey](https://mlsanity.com/paper/2312.17617/) (2023)
- [A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network](https://mlsanity.com/paper/1712.02121/) (2017)
- [Multi-Modal Knowledge Graph Construction and Application: A Survey](https://mlsanity.com/paper/2202.05786/) (2022)
- [Large Language Model based Long-tail Query Rewriting in Taobao Search](https://mlsanity.com/paper/2311.03758/) (2023)
- [Dipping PLMs Sauce: Bridging Structure and Text for Effective Knowledge Graph Completion via Conditional Soft Prompting](https://mlsanity.com/paper/2307.01709/) (2023)
- [Text-Augmented Open Knowledge Graph Completion via Pre-Trained Language Models](https://mlsanity.com/paper/2305.15597/) (2023)

## Built on by (most cited first, 20 of 20)

- [Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation](https://mlsanity.com/paper/2412.18537/) (2024)
- [TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphs](https://mlsanity.com/paper/2502.19512/) (2025)
- [PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments](https://mlsanity.com/paper/2603.23231/) (2026)
- [Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.08519/) (2024)
- [TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework](https://mlsanity.com/paper/2511.05385/) (2025)
- [GS-KGC: A Generative Subgraph-based Framework for Knowledge Graph Completion with Large Language Models](https://mlsanity.com/paper/2408.10819/) (2024)
- [Comprehensive Modeling and Question Answering of Cancer Clinical Practice Guidelines using LLMs](https://mlsanity.com/paper/2501.13984/) (2025)
- [Boosting Knowledge Graph-based Recommendations through Confidence-Aware Augmentation with Large Language Models](https://mlsanity.com/paper/2502.03715/) (2025)
- [MetaLoRA: Tensor-Enhanced Adaptive Low-Rank Fine-tuning](https://mlsanity.com/paper/2504.00460/) (2025)
- [ZeroED: Hybrid Zero-shot Error Detection through Large Language Model Reasoning](https://mlsanity.com/paper/2504.05345/) (2025)
- [HyCE-RAG: Hypergraph Chain-of-Evidence Retrieval-Augmented Generation for Explainable Multi-hop Question Answering](https://mlsanity.com/paper/2607.22597/) (2026)
- [Transformer-Based Multimodal Knowledge Graph Completion with Link-Aware Contexts](https://mlsanity.com/paper/2501.15688/) (2025)
- [OMNIA: Closing the Loop by Leveraging LLMs for Knowledge Graph Completion](https://mlsanity.com/paper/2603.11820/) (2026)
- [Beyond Entity Alignment: Towards Complete Knowledge Graph Alignment via Entity-Relation Synergy](https://mlsanity.com/paper/2407.17745/) (2024)
- [Bridge: A Unified Framework to Knowledge Graph Completion via Language Models and Knowledge Representation](https://mlsanity.com/paper/2411.06660/) (2024)
- [An Interdisciplinary and Cross-Task Review on Missing Data Imputation](https://mlsanity.com/paper/2511.01196/) (2025)
- [Bridging Graph Structure and Knowledge-Guided Editing for Interpretable Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2601.21978/) (2026)
- [Detecting Miscitation on the Scholarly Web through LLM-Augmented Text-Rich Graph Learning](https://mlsanity.com/paper/2603.12290/) (2026)
- [GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion](https://mlsanity.com/paper/2604.21649/) (2026)
- [Generative Representation Learning on Hyper-relational Knowledge Graphs via Masked Discrete Diffusion](https://mlsanity.com/paper/2605.24064/) (2026)

## Abstract (arXiv)

Knowledge graph completion (KGC) is a widely used method to tackle incompleteness in knowledge graphs (KGs) by making predictions for missing links. Description-based KGC leverages pre-trained language models to learn entity and relation representations with their names or descriptions, which shows promising results. However, the performance of description-based KGC is still limited by the quality of text and the incomplete structure, as it lacks sufficient entity descriptions and relies solely on relation names, leading to sub-optimal results. To address this issue, we propose MPIKGC, a general framework to compensate for the deficiency of contextualized knowledge and improve KGC by querying large language models (LLMs) from various perspectives, which involves leveraging the reasoning, explanation, and summarization capabilities of LLMs to expand entity descriptions, understand relations, and extract structures, respectively. We conducted extensive evaluation of the effectiveness and improvement of our framework based on four description-based KGC models and four datasets, for both link prediction and triplet classification tasks.