# Tokenization, Fusion and Decoupling: Bridging the Granularity Mismatch Between Large Language Models and Knowledge Graphs

arXiv: https://arxiv.org/abs/2602.22698 · HTML: https://mlsanity.com/paper/2602.22698/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Builds on (most cited first, 23 of 23)

- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [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)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [Is ChatGPT a General-Purpose Natural Language Processing Task Solver?](https://mlsanity.com/paper/2302.06476/) (2023)
- [KG-BERT: BERT for Knowledge Graph Completion](https://mlsanity.com/paper/1909.03193/) (2019)
- [TuckER: Tensor Factorization for Knowledge Graph Completion](https://mlsanity.com/paper/1901.09590/) (2019)
- [Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph](https://mlsanity.com/paper/2307.07697/) (2023)
- [MMKG: Multi-Modal Knowledge Graphs](https://mlsanity.com/paper/1903.05485/) (2019)
- [Image-embodied Knowledge Representation Learning](https://mlsanity.com/paper/1609.07028/) (2016)
- [Inductive Entity Representations from Text via Link Prediction](https://mlsanity.com/paper/2010.03496/) (2020)
- [Dipping PLMs Sauce: Bridging Structure and Text for Effective Knowledge Graph Completion via Conditional Soft Prompting](https://mlsanity.com/paper/2307.01709/) (2023)
- [IMF: Interactive Multimodal Fusion Model for Link Prediction](https://mlsanity.com/paper/2303.10816/) (2023)
- [MKGL: Mastery of a Three-Word Language](https://mlsanity.com/paper/2410.07526/) (2024)
- [Breaking the Barrier: Utilizing Large Language Models for Industrial Recommendation Systems through an Inferential Knowledge Graph](https://mlsanity.com/paper/2402.13750/) (2024)
- [KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledge](https://mlsanity.com/paper/2405.16412/) (2024)
- [I Know What You Do Not Know: Knowledge Graph Embedding via Co-distillation Learning](https://mlsanity.com/paper/2208.09828/) (2022)
- [Tokenization, Fusion, and Augmentation: Towards Fine-grained Multi-modal Entity Representation](https://mlsanity.com/paper/2404.09468/) (2024)
- [Multiple Heads are Better than One: Mixture of Modality Knowledge Experts for Entity Representation Learning](https://mlsanity.com/paper/2405.16869/) (2024)
- [Towards Faithful Knowledge Graph Explanation Through Deep Alignment in Commonsense Question Answering](https://mlsanity.com/paper/2310.04910/) (2023)

## Abstract (arXiv)

Leveraging Large Language Models (LLMs) for Knowledge Graph Completion (KGC) is promising but hindered by a fundamental granularity mismatch. LLMs operate on fragmented token sequences, whereas entities are the fundamental units in knowledge graphs (KGs) scenarios. Existing approaches typically constrain predictions to limited candidate sets or align entities with the LLM's vocabulary by pooling multiple tokens or decomposing entities into fixed-length token sequences, which fail to capture both the semantic meaning of the text and the structural integrity of the graph. To address this, we propose KGT, a novel framework that uses dedicated entity tokens to enable efficient, full-space prediction. Specifically, we first introduce specialized tokenization to construct feature representations at the level of dedicated entity tokens. We then fuse pre-trained structural and textual features into these unified embeddings via a relation-guided gating mechanism, avoiding training from scratch. Finally, we implement decoupled prediction by leveraging independent heads to separate and combine semantic and structural reasoning. Experimental results show that KGT consistently outperforms state-of-the-art methods across multiple benchmarks.