# Two Heads Are Better Than One: Integrating Knowledge from Knowledge Graphs and Large Language Models for Entity Alignment

arXiv: https://arxiv.org/abs/2401.16960 · HTML: https://mlsanity.com/paper/2401.16960/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 60 references that are in the map.
- First posted on arXiv 30 Jan 2024.

## Builds on (most cited first, 30 of 31)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://mlsanity.com/paper/2104.06378/) (2021)
- [K-BERT: Enabling Language Representation with Knowledge Graph](https://mlsanity.com/paper/1909.07606/) (2019)
- [IntelliCode Compose: Code Generation Using Transformer](https://mlsanity.com/paper/2005.08025/) (2020)
- [Generated Knowledge Prompting for Commonsense Reasoning](https://mlsanity.com/paper/2110.08387/) (2021)
- [Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment](https://mlsanity.com/paper/1611.03954/) (2016)
- [Cross-lingual Entity Alignment via Joint Attribute-Preserving Embedding](https://mlsanity.com/paper/1708.05045/) (2017)
- [Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases](https://mlsanity.com/paper/2106.09231/) (2021)
- [Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs](https://mlsanity.com/paper/1908.08210/) (2019)
- [Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation](https://mlsanity.com/paper/1911.08936/) (2019)
- [Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs](https://mlsanity.com/paper/1905.04914/) (2019)
- [Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network](https://mlsanity.com/paper/1905.11605/) (2019)
- [A Survey on Graph Representation Learning Methods](https://mlsanity.com/paper/2204.01855/) (2022)
- [Empowering News Recommendation with Pre-trained Language Models](https://mlsanity.com/paper/2104.07413/) (2021)
- [A Plug-and-Play Method for Controlled Text Generation](https://mlsanity.com/paper/2109.09707/) (2021)
- [Relational Reflection Entity Alignment](https://mlsanity.com/paper/2008.07962/) (2020)
- [Graph Neural Networks: Taxonomy, Advances and Trends](https://mlsanity.com/paper/2012.08752/) (2020)
- [Neighborhood Matching Network for Entity Alignment](https://mlsanity.com/paper/2005.05607/) (2020)
- [TransEdge: Translating Relation-contextualized Embeddings for Knowledge Graphs](https://mlsanity.com/paper/2004.13579/) (2020)
- [Jointly Learning Entity and Relation Representations for Entity Alignment](https://mlsanity.com/paper/1909.09317/) (2019)
- [Multi-modal Contrastive Representation Learning for Entity Alignment](https://mlsanity.com/paper/2209.00891/) (2022)
- [Collective Entity Alignment via Adaptive Features](https://mlsanity.com/paper/1912.08404/) (2019)
- [JarKA: Modeling Attribute Interactions for Cross-lingual Knowledge Alignment](https://mlsanity.com/paper/1910.13105/) (2019)
- [Degree-Aware Alignment for Entities in Tail](https://mlsanity.com/paper/2005.12132/) (2020)
- [What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data](https://mlsanity.com/paper/2106.06410/) (2021)
- [Are Negative Samples Necessary in Entity Alignment? An Approach with High Performance, Scalability and Robustness](https://mlsanity.com/paper/2108.05278/) (2021)
- [Explicit Knowledge Graph Reasoning for Conversational Recommendation](https://mlsanity.com/paper/2305.00783/) (2023)

## Built on by (most cited first, 8 of 8)

- [CMIE: Combining MLLM Insights with External Evidence for Explainable Out-of-Context Misinformation Detection](https://mlsanity.com/paper/2505.23449/) (2025)
- [Beyond Entity Alignment: Towards Complete Knowledge Graph Alignment via Entity-Relation Synergy](https://mlsanity.com/paper/2407.17745/) (2024)
- [DERA: Dense Entity Retrieval for Entity Alignment in Knowledge Graphs](https://mlsanity.com/paper/2408.01154/) (2024)
- [Full Triple Matcher: Integrating all triple elements between heterogeneous Knowledge Graphs](https://mlsanity.com/paper/2507.22914/) (2025)
- [FLORA: Unsupervised Knowledge Graph Alignment by Fuzzy Logic](https://mlsanity.com/paper/2510.20467/) (2025)
- [Panning for Gold: Expanding Domain-Specific Knowledge Graphs with General Knowledge](https://mlsanity.com/paper/2601.10485/) (2026)
- [EA-Agent: A Structured Multi-Step Reasoning Agent for Entity Alignment](https://mlsanity.com/paper/2604.11686/) (2026)
- [Debate to Align: Reliable Entity Alignment through Two-Stage Multi-Agent Debate](https://mlsanity.com/paper/2604.13551/) (2026)

## Abstract (arXiv)

Entity alignment, which is a prerequisite for creating a more comprehensive Knowledge Graph (KG), involves pinpointing equivalent entities across disparate KGs. Contemporary methods for entity alignment have predominantly utilized knowledge embedding models to procure entity embeddings that encapsulate various similarities-structural, relational, and attributive. These embeddings are then integrated through attention-based information fusion mechanisms. Despite this progress, effectively harnessing multifaceted information remains challenging due to inherent heterogeneity. Moreover, while Large Language Models (LLMs) have exhibited exceptional performance across diverse downstream tasks by implicitly capturing entity semantics, this implicit knowledge has yet to be exploited for entity alignment. In this study, we propose a Large Language Model-enhanced Entity Alignment framework (LLMEA), integrating structural knowledge from KGs with semantic knowledge from LLMs to enhance entity alignment. Specifically, LLMEA identifies candidate alignments for a given entity by considering both embedding similarities between entities across KGs and edit distances to a virtual equivalent entity. It then engages an LLM iteratively, posing multiple multi-choice questions to draw upon the LLM's inference capability. The final prediction of the equivalent entity is derived from the LLM's output. Experiments conducted on three public datasets reveal that LLMEA surpasses leading baseline models. Additional ablation studies underscore the efficacy of our proposed framework.