# Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models

arXiv: https://arxiv.org/abs/2501.18119 · HTML: https://mlsanity.com/paper/2501.18119/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 52 references that are in the map.
- First posted on arXiv 30 Jan 2025.

## Builds on (most cited first, 26 of 26)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Chameleon: Mixed-Modal Early-Fusion Foundation Models](https://mlsanity.com/paper/2405.09818/) (2024)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [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)
- [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://mlsanity.com/paper/2304.13712/) (2023)
- [Composition-based Multi-Relational Graph Convolutional Networks](https://mlsanity.com/paper/1911.03082/) (2019)
- [Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph](https://mlsanity.com/paper/2307.07697/) (2023)
- [A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics](https://mlsanity.com/paper/2310.05694/) (2023)
- [Boosting Language Models Reasoning with Chain-of-Knowledge Prompting](https://mlsanity.com/paper/2306.06427/) (2023)
- [NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs](https://mlsanity.com/paper/2106.12144/) (2021)
- [Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond](https://mlsanity.com/paper/2306.09841/) (2023)
- [Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning](https://mlsanity.com/paper/2410.14211/) (2024)
- [Has Multimodal Learning Delivered Universal Intelligence in Healthcare? A Comprehensive Survey](https://mlsanity.com/paper/2408.12880/) (2024)
- [MKGL: Mastery of a Three-Word Language](https://mlsanity.com/paper/2410.07526/) (2024)
- [KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledge](https://mlsanity.com/paper/2405.16412/) (2024)
- [SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsing](https://mlsanity.com/paper/2406.00562/) (2024)
- [KnowLA: Enhancing Parameter-efficient Finetuning with Knowledgeable Adaptation](https://mlsanity.com/paper/2403.14950/) (2024)
- [Let's Chat to Find the APIs: Connecting Human, LLM and Knowledge Graph through AI Chain](https://mlsanity.com/paper/2309.16134/) (2023)
- [Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability](https://mlsanity.com/paper/2408.07852/) (2024)
- [Random Entity Quantization for Parameter-Efficient Compositional Knowledge Graph Representation](https://mlsanity.com/paper/2310.15797/) (2023)
- [PathReasoner: Modeling Reasoning Path with Equivalent Extension for Logical Question Answering](https://mlsanity.com/paper/2405.19109/) (2024)

## Built on by (most cited first, 11 of 11)

- [CodeBrain: Bridging Decoupled Tokenizer and Multi-Scale Architecture for EEG Foundation Model](https://mlsanity.com/paper/2506.09110/) (2025)
- [MARS: Multi-Agent Adaptive Reasoning with Socratic Guidance for Automated Prompt Optimization](https://mlsanity.com/paper/2503.16874/) (2025)
- [Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey](https://mlsanity.com/paper/2507.22920/) (2025)
- [GKG-LLM: A Unified Framework for Generalized Knowledge Graph Construction](https://mlsanity.com/paper/2503.11227/) (2025)
- [Toward Clinically Explainable AI for Medical Diagnosis: A Foundation Model with Human-Compatible Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2509.03906/) (2025)
- [EH-Benchmark Ophthalmic Hallucination Benchmark and Agent-Driven Top-Down Traceable Reasoning Workflow](https://mlsanity.com/paper/2507.22929/) (2025)
- [<SOG_k>: One LLM Token for Explicit Graph Structural Understanding](https://mlsanity.com/paper/2602.01771/) (2026)
- [ReaLM: Residual Quantization Bridging Knowledge Graph Embeddings and Large Language Models](https://mlsanity.com/paper/2510.09711/) (2025)
- [Beyond Prefixes: Graph-as-Memory Cross-Attention for Knowledge Graph Completion with Large Language Models](https://mlsanity.com/paper/2510.08966/) (2025)
- [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)

Due to the presence of the natural gap between Knowledge Graph (KG) structures and the natural language, the effective integration of holistic structural information of KGs with Large Language Models (LLMs) has emerged as a significant question. To this end, we propose a two-stage framework to learn and apply quantized codes for each entity, aiming for the seamless integration of KGs with LLMs. Firstly, a self-supervised quantized representation (SSQR) method is proposed to compress both KG structural and semantic knowledge into discrete codes (ie, tokens) that align the format of language sentences. We further design KG instruction-following data by viewing these learned codes as features to directly input to LLMs, thereby achieving seamless integration. The experiment results demonstrate that SSQR outperforms existing unsupervised quantized methods, producing more distinguishable codes. Further, the fine-tuned LLaMA2 and LLaMA3.1 also have superior performance on KG link prediction and triple classification tasks, utilizing only 16 tokens per entity instead of thousands in conventional prompting methods.