TrackLGD: Tracking layer-wise graph dynamics for reliable hallucination detection in large language models
Authors:
- Linggang KongLKLinggang Kong
- Haoran FuHFHaoran Fu
- Aiye LiALAiye Li
- Lei WuLWLei Wu
- Junyu HengJHJunyu Heng
- Xiaofeng ZhongXZXiaofeng Zhong
- Yongjie WangYWYongjie Wang
- 5 August 2026
- journal article
- Published by Elsevier in Information Sciences
- Vol. 758
Abstract
No abstract availableThis publication has 8 references indexed in Scilit:
- Multi-perspective consistency checking for large language model hallucination detection: a black-box zero-resource approachFrontiers of Information Technology & Electronic Engineering, 2025
- LLM-LADE: Large language model-based log anomaly detection with explanationKnowledge-Based Systems, 2025
- Prescribing the right remedy: Mitigating hallucinations in large vision-language models via targeted instruction tuningInformation Sciences, 2025
- HaluCheck: Explainable and verifiable automation for detecting hallucinations in LLM responsesExpert Systems with Applications, 2025
- A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open QuestionsACM Transactions on Information Systems, 2025
- Relation-aware multiplex heterogeneous graph neural networkKnowledge-Based Systems, 2024
- Know where to go: Make LLM a relevant, responsible, and trustworthy searchersDecision Support Systems, 2024
- Detecting hallucinations in large language models using semantic entropyNature, 2024