# Interpretable Unsupervised Community Detection with LLM-Symbolized Structured Processes

arXiv: https://arxiv.org/abs/2608.06402 · HTML: https://mlsanity.com/paper/2608.06402/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 42 references that are in the map.
- First posted on arXiv 2 Aug 2026.

## Builds on (most cited first, 14 of 14)

- [From Louvain to Leiden: guaranteeing well-connected communities](https://mlsanity.com/paper/1810.08473/) (2018)
- [Learning on Large-scale Text-attributed Graphs via Variational Inference](https://mlsanity.com/paper/2210.14709/) (2022)
- [Structural Deep Clustering Network](https://mlsanity.com/paper/2002.01633/) (2020)
- [GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph](https://mlsanity.com/paper/2105.02605/) (2021)
- [Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction](https://mlsanity.com/paper/2111.00064/) (2021)
- [Can GNN be Good Adapter for LLMs?](https://mlsanity.com/paper/2402.12984/) (2024)
- [Train Your Own GNN Teacher: Graph-Aware Distillation on Textual Graphs](https://mlsanity.com/paper/2304.10668/) (2023)
- [Evaluating Generative Models for Graph-to-Text Generation](https://mlsanity.com/paper/2307.14712/) (2023)
- [CLARE: A Semi-supervised Community Detection Algorithm](https://mlsanity.com/paper/2210.08274/) (2022)
- [Efficient Unsupervised Community Search with Pre-trained Graph Transformer](https://mlsanity.com/paper/2403.18869/) (2024)
- [Neural Attributed Community Search at Billion Scale](https://mlsanity.com/paper/2403.18874/) (2024)
- [Pre-train and Refine: Towards Higher Efficiency in K-Agnostic Community Detection without Quality Degradation](https://mlsanity.com/paper/2405.20277/) (2024)
- [ProCom: A Few-shot Targeted Community Detection Algorithm](https://mlsanity.com/paper/2408.07369/) (2024)
- [Ensemble-based Deep Multilayer Community Search](https://mlsanity.com/paper/2501.02194/) (2025)

## Abstract (arXiv)

Community detection is a fundamental task in graph analytics that aims to identify cohesive groups of entities with similar behaviors or interests. Classic objective-driven methods struggle with complex graph structures, while deep-learning approaches improve performance at the expense of interpretability and rely on labeled data and training. Large language models (LLMs), with strong reasoning capabilities and world knowledge, are promising for interpretable, label-free community detection. To leverage these strengths, we propose LUCID, an LLM-guided, interpretable, training-free, and unsupervised community detection method. Inspired by phase-transition kinetics in natural systems, where complex structures emerge through initialization, merging, refinement, and selection, LUCID is designed as a four-stage pipeline. Within this pipeline, the LLM induces formal rules that translate implicit knowledge into explicit and interpretable logical structures. Specifically, (1) the Local-View Community Initialization stage encodes local graph structures using k-ego contexts and unsupervised node roles; (2) the Multi-factor Community Merge stage uses LLM-induced rules to iteratively merge local communities; (3) the Multi-grain Community Refinement stage applies LLM-induced coarse-to-fine rules in parallel to reduce boundary noise; and (4) the Global-view Community Selection stage identifies high-quality communities based on topological compactness and boundary clarity. Extensive experiments on real-world datasets demonstrate that LUCID, as an unsupervised approach, achieves state-of-the-art performance and consistently outperforms leading unsupervised and semi-supervised baselines.