Mitigating GenAI-powered Evidence Pollution for Out-of-Context Misinformation Detection

Zehong Yan, Peng Qi, Wynne Hsu, Mong Li Lee
National University of Singapore

ICDE, 2026 / PDF / Project Page / Code / Data

We investigate how polluted evidence affects the performance of existing OOC detectors, revealing a performance degradation of more than 9 percentage points. We further propose two strategies, cross-modal evidence reranking and cross-modal claim-evidence reasoning, to address the challenges posed by polluted evidence.

TRUST-VL: A Unified and Explainable Vision–Language Model for General Multimodal Misinformation Detection

Zehong Yan, Peng Qi, Wynne Hsu, Mong Li Lee
▶ National University of Singapore

EMNLP, 2025 (Oral) / PDF / Project Page / Code

We present a unified and explainable vision–language model for various multimodal misinformation detection tasks across textual, visual, and cross-modal distortions, enhanced by the Question-Aware Visual Amplifier (QAVA) and supported by the large-scale TRUST-Instruct dataset of 198K reasoning samples.

Modeling Complex Interactions in Long Documents for Aspect-Based Sentiment Analysis

Zehong Yan¹, Wynne Hsu¹, Mong Li Lee¹, David Roy Bartram-Shaw²
¹NUS Centre for Trusted Internet & Community, National University of Singapore
²Edelman Data & Intelligence

WASSA Workshop, ACL, 2024 / PDF / Project Page / Code / Data

We introduce DART, a hierarchical transformer-based framework for aspect-based sentiment analysis in long documents. DART handles the complexities of longer text through its global context interaction and two-level aspect-specific aggregation blocks. For empirical validation, we curate two datasets for aspect-based sentiment analysis in long documents: SocialNews and TrustData.

SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection

Peng Qi, Zehong Yan, Wynne Hsu, Mong Li Lee
National University of Singapore

CVPR, 2024 / PDF / Project Page / Code / Video

Focusing on the innovative research perspective of explainable out-of-context misinformation detection, this paper proposes a new multimodal large language model, SNIFFER, designed to offer both accurate detection and persuasive explanations simultaneously. Enhanced by two-stage instruction tuning and retrieval-enhancement techniques, SNIFFER effectively models both internal image-text inconsistency and external claim-evidence relationships.