# LLM-Powered Text-Attributed Graph Anomaly Detection via Retrieval-Augmented Reasoning

arXiv: https://arxiv.org/abs/2511.17584 · HTML: https://mlsanity.com/paper/2511.17584/

## Key facts

- Cited by 2 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 17 of its 40 references that are in the map.
- First posted on arXiv 16 Nov 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- Retrieval-augmented generation / [Privacy and security of RAG](https://mlsanity.com/rag/privacy-and-security-of-rag/)

## Builds on (most cited first, 17 of 17)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks](https://mlsanity.com/paper/2007.02901/) (2020)
- [GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarking](https://mlsanity.com/paper/2305.15066/) (2023)
- [Talk like a Graph: Encoding Graphs for Large Language Models](https://mlsanity.com/paper/2310.04560/) (2023)
- [Language agents achieve superhuman synthesis of scientific knowledge](https://mlsanity.com/paper/2409.13740/) (2024)
- [Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning](https://mlsanity.com/paper/2305.19523/) (2023)
- [GraphText: Graph Reasoning in Text Space](https://mlsanity.com/paper/2310.01089/) (2023)
- [Prompt-based Node Feature Extractor for Few-shot Learning on Text-Attributed Graphs](https://mlsanity.com/paper/2309.02848/) (2023)
- [LEGO-Learn: Label-Efficient Graph Open-Set Learning](https://mlsanity.com/paper/2410.16386/) (2024)
- [Graph Synthetic Out-of-Distribution Exposure with Large Language Models](https://mlsanity.com/paper/2504.21198/) (2025)
- [Text-Attributed Graph Anomaly Detection via Multi-Scale Cross- and Uni-Modal Contrastive Learning](https://mlsanity.com/paper/2508.00513/) (2025)
- [Court of LLMs: Evidence-Augmented Generation via Multi-LLM Collaboration for Text-Attributed Graph Anomaly Detection](https://mlsanity.com/paper/2508.00507/) (2025)

## Built on by (most cited first, 2 of 2)

- [ProTAGAD: A Foundation Model for TAG Anomaly Detection with Decoupled Topological and Textual Prototypes](https://mlsanity.com/paper/2608.10699/) (2026)
- [GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMs](https://mlsanity.com/paper/2609.12265/) (2026)

## Abstract (arXiv)

Anomaly detection on attributed graphs plays an essential role in applications such as fraud detection, intrusion monitoring, and misinformation analysis. However, text-attributed graphs (TAGs), in which node information is expressed in natural language, remain underexplored, largely due to the absence of standardized benchmark datasets. In this work, we introduce TAG-AD, a comprehensive benchmark for anomaly node detection on TAGs. TAG-AD leverages large language models (LLMs) to generate realistic anomalous node texts directly in the raw text space, producing anomalies that are semantically coherent yet contextually inconsistent and thus more reflective of real-world irregularities. In addition, TAG-AD incorporates multiple other anomaly types, enabling thorough and reproducible evaluation of graph anomaly detection (GAD) methods. With these datasets, we further benchmark existing unsupervised GNN-based GAD methods as well as zero-shot LLMs for GAD. As part of our zero-shot detection setup, we propose a retrieval-augmented generation (RAG)-assisted, LLM-based zero-shot anomaly detection framework. The framework mitigates reliance on brittle, hand-crafted prompts by constructing a global anomaly knowledge base and distilling it into reusable analysis frameworks. Our experimental results reveal a clear division of strengths: LLMs are particularly effective at detecting contextual anomalies, whereas GNN-based methods remain superior for structural anomaly detection. Moreover, RAG-assisted prompting achieves performance comparable to human-designed prompts while eliminating manual prompt engineering, underscoring the practical value of our RAG-assisted zero-shot LLM anomaly detection framework.