# Large Language Models Can Better Understand Knowledge Graphs Than We Thought

arXiv: https://arxiv.org/abs/2402.11541 · HTML: https://mlsanity.com/paper/2402.11541/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 34 of its 50 references that are in the map.
- First posted on arXiv 18 Feb 2024.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 30 of 34)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [ERNIE: Enhanced Language Representation with Informative Entities](https://mlsanity.com/paper/1905.07129/) (2019)
- [StructGPT: A General Framework for Large Language Model to Reason over Structured Data](https://mlsanity.com/paper/2305.09645/) (2023)
- [K-BERT: Enabling Language Representation with Knowledge Graph](https://mlsanity.com/paper/1909.07606/) (2019)
- [Generate rather than Retrieve: Large Language Models are Strong Context Generators](https://mlsanity.com/paper/2209.10063/) (2022)
- [MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries](https://mlsanity.com/paper/2401.15391/) (2024)
- [DocRED: A Large-Scale Document-Level Relation Extraction Dataset](https://mlsanity.com/paper/1906.06127/) (2019)
- [Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning](https://mlsanity.com/paper/2305.14160/) (2023)
- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [Variational Reasoning for Question Answering with Knowledge Graph](https://mlsanity.com/paper/1709.04071/) (2017)
- [Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering](https://mlsanity.com/paper/2306.04136/) (2023)
- [Large Language Models are few(1)-shot Table Reasoners](https://mlsanity.com/paper/2210.06710/) (2022)
- [Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model](https://mlsanity.com/paper/1912.09637/) (2019)
- [An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labels](https://mlsanity.com/paper/2203.11364/) (2022)
- [Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvements](https://mlsanity.com/paper/2401.06766/) (2024)
- [KQA Pro: A Dataset with Explicit Compositional Programs for Complex Question Answering over Knowledge Base](https://mlsanity.com/paper/2007.03875/) (2020)
- [MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models](https://mlsanity.com/paper/2308.09729/) (2023)
- [Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family](https://mlsanity.com/paper/2303.07992/) (2023)
- [Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answering](https://mlsanity.com/paper/2309.11206/) (2023)
- [Graph Reasoning for Question Answering with Triplet Retrieval](https://mlsanity.com/paper/2305.18742/) (2023)
- [Open Domain Question Answering with A Unified Knowledge Interface](https://mlsanity.com/paper/2110.08417/) (2021)
- [Inductive Relation Prediction by BERT](https://mlsanity.com/paper/2103.07102/) (2021)
- [KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graph](https://mlsanity.com/paper/2312.15880/) (2023)

## Built on by (most cited first, 10 of 10)

- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [Automating Data-Driven Modeling and Analysis for Engineering Applications using Large Language Model Agents](https://mlsanity.com/paper/2510.01398/) (2025)
- [Construct, Align, and Reason: Large Ontology Models for Enterprise Knowledge Management](https://mlsanity.com/paper/2602.00029/) (2026)
- [Knowledge Graph Representations for LLM-Based Policy Compliance Reasoning](https://mlsanity.com/paper/2604.27713/) (2026)
- [The Structure-Content Trade-off in Knowledge Graph Retrieval](https://mlsanity.com/paper/2506.13380/) (2025)
- [Knowledge Fusion via Bidirectional Information Aggregation](https://mlsanity.com/paper/2507.08704/) (2025)
- [Cross-domain Multi-step Thinking: Zero-shot Fine-grained Traffic Sign Recognition in the Wild](https://mlsanity.com/paper/2409.01534/) (2024)
- [Nested Episodic State Topology (NEST): A Graph-Theoretic Architecture of Cognitive States](https://mlsanity.com/paper/2607.06055/) (2026)
- [The Answer Path and the Grounding Instruction in LLM Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2609.10237/) (2026)
- [Semantic Abstraction for Natural Language Inference: a Methodological Framework for Discovering and Compensating Semantic Knowledge and Reasoning Gaps in Large Language Models](https://mlsanity.com/paper/2609.26610/) (2026)

## Abstract (arXiv)

When we integrate factual knowledge from knowledge graphs (KGs) into large language models (LLMs) to enhance their performance, the cost of injection through training increases with the scale of the models. Consequently, there is significant interest in developing prompt strategies that effectively incorporate KG information into LLMs. However, the community has not yet comprehensively understood how LLMs process and interpret KG information in different input formats and organizations within prompts, and researchers often rely on trial and error. To address this gap, we design extensive experiments to empirically study LLMs' comprehension of different KG prompts. At the literal level, we reveal LLMs' preferences for various input formats (from linearized triples to fluent natural language text). At the attention distribution level, we discuss the underlying mechanisms driving these preferences. We then investigate how the organization of structured knowledge impacts LLMs and evaluate LLMs' robustness in processing and utilizing KG information in practical scenarios. Our experiments show that (1) linearized triples are more effective than fluent NL text in helping LLMs understand KG information and answer fact-intensive questions; (2) Different LLMs exhibit varying preferences for different organizational formats of triples; (3) LLMs with larger scales are more susceptible to noisy, incomplete subgraphs.