Both Topology and Text Matter: Revisiting LLM-guided Out-of-Distribution Detection on Text-attributed Graphs
Preprint
Abstract
Text-attributed graphs (TAGs) associate nodes with textual attributes and graph structure, enabling GNNs to jointly model semantic and structural information. While effective on in-distribution (ID) data, GNNs often encounter out-of-distribution (OOD) nodes with unseen textual or structural patterns in real-world settings, leading to overconfident and erroneous predictions in the absence of reliable OOD detection. Early approaches address this issue from a topology-driven perspective, leveraging neighboring structures to mitigate node-level detection bias. However, these methods typically encode node texts as shallow vector features, failing to fully exploit rich semantic information. In contrast, recent LLM-based approaches generate pseudo OOD priors by leveraging textual knowledge, but they suffer from several limitations: (1) a reliability-informativeness imbalance in the synthesized OOD priors, as the generated OOD exposures either deviate from the true OOD semantics, or introduce non-negligible ID noise, all of which offers limited improvement to detection performance; (2) reliance on specialized architectures, which prevents incorporation of the extensive effective topology-level insights that have been empirically validated in prior work. To this end, we propose LG-Plug, an LLM-Guided Plug-and-play strategy for TAG OOD detection tasks. LG-Plug aligns topology and text representations to produce fine-grained node embeddings, then generates consensus-driven OOD exposure via clustered iterative LLM prompting. Moreover, it leverages lightweight in-cluster codebook and heuristic sampling reduce time cost of LLM querying. The resulting OOD exposure serves as a regularization term to separate ID and OOD nodes, enabling seamless integration with existing detectors.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- GraphLLM: Boosting Graph Reasoning Ability of Large Language ModelIEEE Transactions on Big Data, 2025
- A Survey of Graph Neural Networks for Social Recommender SystemsACM Computing Surveys, 2024
- Revisiting Score Propagation in Graph Out-of-Distribution Detection2024
- Can Language Models Solve Graph Problems in Natural Language?2023
- Graph Neural Networks: Taxonomy, Advances, and TrendsACM Transactions on Intelligent Systems and Technology, 2022
- GOOD: A Graph Out-Of-Distribution Benchmark2022
- Open-CyKG: An Open Cyber Threat Intelligence Knowledge GraphKnowledge-Based Systems, 2021
- A Comprehensive Survey on Graph Neural NetworksIEEE Transactions on Neural Networks and Learning Systems, 2020
- Least squares quantization in PCMIEEE Transactions on Information Theory, 1982