Unmasking Fake Careers: Detecting Machine-Generated Career Trajectories via Multi-layer Heterogeneous Graphs

2025-09-23

AI Summary

Large language models (LLMs) pose a novel security threat by generating fabricated professional trajectories in resumes, undermining hiring integrity and trust. Method: We propose the first structured detection framework specifically designed for career-path authenticity verification. Our approach introduces a heterogeneous career trajectory graph model—integrating job titles, organizations, temporal attributes, and their interrelations into a global-local, multi-layer heterogeneous graph—and designs a structure-aware graph neural network that learns synthetic artifacts via trustworthy neighborhood aggregation and cross-layer information propagation. Contribution/Results: Evaluated on a large-scale, real-world career relationship graph and a manually annotated dataset of AI-generated trajectories, our method significantly outperforms existing SOTA approaches across multiple metrics, achieving relative accuracy improvements of 5.8%–85.0%. It establishes an interpretable, scalable, and structurally grounded paradigm for detecting AI-generated content in professional documentation.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

The rapid advancement of Large Language Models (LLMs) has enabled the generation of highly realistic synthetic data. We identify a new vulnerability, LLMs generating convincing career trajectories in fake resumes and explore effective detection methods. To address this challenge, we construct a dataset of machine-generated career trajectories using LLMs and various methods, and demonstrate that conventional text-based detectors perform poorly on structured career data. We propose CareerScape, a novel heterogeneous, hierarchical multi-layer graph framework that models career entities and their relations in a unified global graph built from genuine resumes. Unlike conventional classifiers that treat each instance independently, CareerScape employs a structure-aware framework that augments user-specific subgraphs with trusted neighborhood information from a global graph, enabling the model to capture both global structural patterns and local inconsistencies indicative of synthetic career paths. Experimental results show that CareerScape outperforms state-of-the-art baselines by 5.8-85.0% relatively, highlighting the importance of structure-aware detection for machine-generated content.

Problem

• Detecting machine-generated career trajectories in fake resumes using multi-layer graphs
• Addressing poor performance of text-based detectors on structured career data
• Capturing global structural patterns and local inconsistencies in synthetic career paths

Innovation

• Multi-layer heterogeneous graphs model career entities and relations
• Structure-aware framework augments user subgraphs with neighborhood information
• Global structural patterns and local inconsistencies detect synthetic paths