# Colorful Talks with Graphs: Human-Interpretable Graph Encodings for Large Language Models

arXiv: https://arxiv.org/abs/2602.10386 · HTML: https://mlsanity.com/paper/2602.10386/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 30 references that are in the map.
- First posted on arXiv 11 Feb 2026.

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

- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Can Language Models Solve Graph Problems in Natural Language?](https://mlsanity.com/paper/2305.10037/) (2023)
- [Language is All a Graph Needs](https://mlsanity.com/paper/2308.07134/) (2023)
- [GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarking](https://mlsanity.com/paper/2305.15066/) (2023)
- [Large Language Models on Graphs: A Comprehensive Survey](https://mlsanity.com/paper/2312.02783/) (2023)
- [LLaGA: Large Language and Graph Assistant](https://mlsanity.com/paper/2402.08170/) (2024)
- [Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs](https://mlsanity.com/paper/2404.07103/) (2024)
- [GraphText: Graph Reasoning in Text Space](https://mlsanity.com/paper/2310.01089/) (2023)
- [A Survey of Large Language Models for Graphs](https://mlsanity.com/paper/2405.08011/) (2024)
- [Understanding Transformer Reasoning Capabilities via Graph Algorithms](https://mlsanity.com/paper/2405.18512/) (2024)
- [UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs](https://mlsanity.com/paper/2402.13630/) (2024)
- [Can we Soft Prompt LLMs for Graph Learning Tasks?](https://mlsanity.com/paper/2402.10359/) (2024)
- [LLM4DyG: Can Large Language Models Solve Spatial-Temporal Problems on Dynamic Graphs?](https://mlsanity.com/paper/2310.17110/) (2023)
- [Disentangled Representation Learning with Large Language Models for Text-Attributed Graphs](https://mlsanity.com/paper/2310.18152/) (2023)
- [GREED: A Neural Framework for Learning Graph Distance Functions](https://mlsanity.com/paper/2112.13143/) (2021)
- [Large Language Models as Topological Structure Enhancers for Text-Attributed Graphs](https://mlsanity.com/paper/2311.14324/) (2023)
- [LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models](https://mlsanity.com/paper/2503.03313/) (2025)
- [GraphICL: Unlocking Graph Learning Potential in LLMs through Structured Prompt Design](https://mlsanity.com/paper/2501.15755/) (2025)
- [Graph-oriented Instruction Tuning of Large Language Models for Generic Graph Mining](https://mlsanity.com/paper/2403.04780/) (2024)
- [Are Large Language Models In-Context Graph Learners?](https://mlsanity.com/paper/2502.13562/) (2025)
- [Similarity-based Neighbor Selection for Graph LLMs](https://mlsanity.com/paper/2402.03720/) (2024)
- [From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context](https://mlsanity.com/paper/2508.07117/) (2025)

## Built on by (most cited first, 1 of 1)

- [GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMs](https://mlsanity.com/paper/2609.12265/) (2026)

## Abstract (arXiv)

Graph problems are fundamentally challenging for large language models (LLMs). While LLMs excel at processing unstructured text, graph tasks require reasoning over explicit structure, permutation invariance, and computationally complex relationships, creating a mismatch with the representations of text-based models. Our work investigates how LLMs can be effectively applied to graph problems despite these barriers. We introduce a human-interpretable structural encoding strategy for graph-to-text translation that injects graph structure directly into natural language prompts. Our method involves computing a variant of Weisfeiler-Lehman (WL) similarity classes and maps them to human-like color tokens rather than numeric labels. The key insight is that semantically meaningful and human-interpretable cues may be more effectively processed by LLMs than opaque symbolic encoding. Experimental results on multiple algorithmic and predictive graph tasks show the considerable improvements by our method on both synthetic and real-world datasets. By capturing both local and global-range dependencies, our method enhances LLM performance especially on graph tasks that require reasoning over global graph structure.