Papers by Delvin Ce Zhang
Unmasking Fake Careers: Detecting Machine-Generated Career Trajectories via Multi-layer Heterogeneous Graphs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) generate convincing career trajectories in fake resumes . a novel heterogeneous, hierarchical multi-layer graph framework is proposed to model career entities and their relations in a unified global graph built from genuine resumes. |
| Approach: | They propose a novel heterogeneous, hierarchical multi-layer graph framework that models career entities and their relations in a unified global graph built from genuine resumes. |
| Outcome: | The proposed framework outperforms state-of-the-art models by 5.8-85.0% relative to baselines. |
When Misinformation Speaks and Converses: Rethinking Fact-Checking in Audio Platforms (2026.acl-long)
Copied to clipboard
| Challenge: | Existing fact-checking pipelines focus on written claims, not on audio . authors argue that audio misinformation is structurally different because it is both spoken and conversational . |
| Approach: | They argue that audio misinformation is structurally different because it is both spoken and conversational . they argue that advancing fact-checking requires rethinking verification pipelines around spoken and conversations . |
| Outcome: | The proposed method fails on audio because it is both spoken and conversational . podcasts exceed 4.3 million distinct shows, reaching an estimated 500 million listeners globally . |
SUA: Stealthy Multimodal Large Language Model Unlearning Attack (2025.emnlp-main)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) trained on massive data may memorize sensitive personal information and photos, posing privacy and copyright concerns. |
| Approach: | They propose a framework that learns a universal noise pattern to recover unlearned information from MLLMs. |
| Outcome: | The proposed framework learns a universal noise pattern and can reveal unlearned content when applied to images. |
MEVER: Multi-Modal and Explainable Claim Verification with Graph-based Evidence Retrieval (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing methods for verification of claims rely on textual evidence only or ignore the explainability. |
| Approach: | They propose a multi-modal reasoning model that integrates text and visual evidence for verification. |
| Outcome: | The proposed model achieves evidence retrieval, multi-modal claim verification, and explanation generation. |
CORRECT: Context- and Reference-Augmented Reasoning and Prompting for Fact-Checking (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing fact-checking models focus on reasoning within evidence sentences, but they ignore auxiliary contexts and references. |
| Approach: | They propose a method to verify the truthfulness of claims using evidence . they construct a three-layer evidence graph with evidence, context, and reference layers . |
| Outcome: | The proposed method can verify the truthfulness of claims using evidence . it integrates evidence, context, and reference layers into a unified embedding . |