Court of LLMs: Evidence-Augmented Generation via Multi-LLM Collaboration for Text-Attributed Graph Anomaly Detection

• URL: http://arxiv.org/abs/2508.00507v1
• Date: Fri, 01 Aug 2025 10:36:39 GMT
• Title: Court of LLMs: Evidence-Augmented Generation via Multi-LLM Collaboration for Text-Attributed Graph Anomaly Detection
• Authors: Yiming Xu, Jiarun Chen, Zhen Peng, Zihan Chen, Qika Lin, Lan Ma, Bin Shi, Bo Dong,
• Abstract summary: Large language models (LLMs) have emerged as promising alternatives due to their strong semantic understanding and reasoning capabilities.<n>We propose CoLL, a novel framework that combines LLMs and graph neural networks (GNNs) to leverage their complementary strengths.
• Score: 21.810411783179593
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The natural combination of intricate topological structures and rich textual information in text-attributed graphs (TAGs) opens up a novel perspective for graph anomaly detection (GAD). However, existing GAD methods primarily focus on designing complex optimization objectives within the graph domain, overlooking the complementary value of the textual modality, whose features are often encoded by shallow embedding techniques, such as bag-of-words or skip-gram, so that semantic context related to anomalies may be missed. To unleash the enormous potential of textual modality, large language models (LLMs) have emerged as promising alternatives due to their strong semantic understanding and reasoning capabilities. Nevertheless, their application to TAG anomaly detection remains nascent, and they struggle to encode high-order structural information inherent in graphs due to input length constraints. For high-quality anomaly detection in TAGs, we propose CoLL, a novel framework that combines LLMs and graph neural networks (GNNs) to leverage their complementary strengths. CoLL employs multi-LLM collaboration for evidence-augmented generation to capture anomaly-relevant contexts while delivering human-readable rationales for detected anomalies. Moreover, CoLL integrates a GNN equipped with a gating mechanism to adaptively fuse textual features with evidence while preserving high-order topological information. Extensive experiments demonstrate the superiority of CoLL, achieving an average improvement of 13.37% in AP. This study opens a new avenue for incorporating LLMs in advancing GAD.

Related papers

• Text-Attributed Graph Anomaly Detection via Multi-Scale Cross- and Uni-Modal Contrastive Learning [19.634966556695897]
  This paper presents a novel end-to-end paradigm for text-attributed graph anomaly detection, named CMUCL.<n>We simultaneously model data from both text and graph structures, and jointly train text and graph encoders by leveraging cross-modal and uni-modal estimator multi-scale consistency to uncover potential anomaly-related information.
  arXiv  Detail & Related papers  (2025-08-01T10:47:07Z)
• DGP: A Dual-Granularity Prompting Framework for Fraud Detection with Graph-Enhanced LLMs [55.13817504780764]
  Real-world fraud detection applications benefit from graph learning techniques that jointly exploit node features, often rich in textual data, and graph structural information.<n>Graph-Enhanced LLMs emerge as a promising graph learning approach that converts graph information into prompts.<n>We propose Dual Granularity Prompting (DGP), which mitigates information overload by preserving fine-grained textual details for the target node.
  arXiv  Detail & Related papers  (2025-07-29T10:10:47Z)
• Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering [75.12322966980003]
  Large Language Models (LLMs) have shown strong inductive reasoning ability across various domains.<n>Most existing RAG pipelines rely on unstructured text, limiting interpretability and structured reasoning.<n>Recent studies have explored integrating knowledge graphs with LLMs for knowledge graph question answering.<n>We propose RAPL, a novel framework for efficient and effective graph retrieval in KGQA.
  arXiv  Detail & Related papers  (2025-06-11T12:03:52Z)
• Align-GRAG: Reasoning-Guided Dual Alignment for Graph Retrieval-Augmented Generation [75.9865035064794]
  Large language models (LLMs) have demonstrated remarkable capabilities, but still struggle with issues like hallucinations and outdated information.<n>Retrieval-augmented generation (RAG) addresses these issues by grounding LLM outputs in external knowledge with an Information Retrieval (IR) system.<n>We propose Align-GRAG, a novel reasoning-guided dual alignment framework in post-retrieval phrase.
  arXiv  Detail & Related papers  (2025-05-22T05:15:27Z)
• A Tripartite Perspective on GraphRAG [0.0]
  Large Language Models (LLMs) have shown remarkable capabilities across various domains, yet they struggle with knowledge-intensive tasks.<n>Key limitations include their tendency to hallucinate, lack of source traceability (provenance), and challenges in timely knowledge updates.<n>We propose a novel approach that combines LLMs with a tripartite knowledge graph representation.
  arXiv  Detail & Related papers  (2025-04-28T10:43:35Z)
• Hallucination Detection in LLMs with Topological Divergence on Attention Graphs [64.74977204942199]
  Hallucination, i.e., generating factually incorrect content, remains a critical challenge for large language models.<n>We introduce TOHA, a TOpology-based HAllucination detector in the RAG setting.
  arXiv  Detail & Related papers  (2025-04-14T10:06:27Z)
• Advanced Text Analytics -- Graph Neural Network for Fake News Detection in Social Media [0.0]
  Advanced Text Analysis Graph Neural Network (ATA-GNN) is proposed in this paper.<n>ATA-GNN employs innovative topic modelling (clustering) techniques to identify typical words for each topic.<n>Extensive evaluations on widely used benchmark datasets demonstrate that ATA-GNN surpasses the performance of current GNN-based FND methods.
  arXiv  Detail & Related papers  (2025-02-22T09:17:33Z)
• Deep Graph Anomaly Detection: A Survey and New Perspectives [86.84201183954016]
  Graph anomaly detection (GAD) aims to identify unusual graph instances (nodes, edges, subgraphs, or graphs)<n>Deep learning approaches, graph neural networks (GNNs) in particular, have been emerging as a promising paradigm for GAD.
  arXiv  Detail & Related papers  (2024-09-16T03:05:11Z)
• Unleashing the Potential of Text-attributed Graphs: Automatic Relation Decomposition via Large Language Models [31.443478448031886]
  RoSE (Relation-oriented Semantic Edge-decomposition) is a novel framework that decomposes the graph structure by analyzing raw text attributes. Our framework significantly enhances node classification performance across various datasets, with improvements of up to 16% on the Wisconsin dataset.
  arXiv  Detail & Related papers  (2024-05-28T20:54:47Z)
• G-SAP: Graph-based Structure-Aware Prompt Learning over Heterogeneous Knowledge for Commonsense Reasoning [8.02547453169677]
  We propose a novel Graph-based Structure-Aware Prompt Learning Model for commonsense reasoning, named G-SAP. In particular, an evidence graph is constructed by integrating multiple knowledge sources, i.e. ConceptNet, Wikipedia, and Cambridge Dictionary. The results reveal a significant advancement over the existing models, especially, with 6.12% improvement over the SoTA LM+GNNs model on the OpenbookQA dataset.
  arXiv  Detail & Related papers  (2024-05-09T08:28:12Z)
• BOURNE: Bootstrapped Self-supervised Learning Framework for Unified Graph Anomaly Detection [50.26074811655596]
  We propose a novel unified graph anomaly detection framework based on bootstrapped self-supervised learning (named BOURNE) By swapping the context embeddings between nodes and edges, we enable the mutual detection of node and edge anomalies. BOURNE can eliminate the need for negative sampling, thereby enhancing its efficiency in handling large graphs.
  arXiv  Detail & Related papers  (2023-07-28T00:44:57Z)
• Graph Representation Learning via Graphical Mutual Information Maximization [86.32278001019854]
  We propose a novel concept, Graphical Mutual Information (GMI), to measure the correlation between input graphs and high-level hidden representations. We develop an unsupervised learning model trained by maximizing GMI between the input and output of a graph neural encoder.
  arXiv  Detail & Related papers  (2020-02-04T08:33:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.