{"total":14,"rows":[{"id":"2403.03170","title":"SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection","created":"2024-03-05","cited_by_count":74,"area":"mllm"},{"id":"2311.13258","title":"ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation","created":"2023-11-22","cited_by_count":13,"area":"mllm"},{"id":"2403.03627","title":"Multimodal Large Language Models to Support Real-World Fact-Checking","created":"2024-03-06","cited_by_count":13,"area":"mllm"},{"id":"2409.19656","title":"Multimodal Misinformation Detection by Learning from Synthetic Data with Multimodal LLMs","created":"2024-09-29","cited_by_count":13,"area":"mllm"},{"id":"2503.15024","title":"Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Models","created":"2025-03-19","cited_by_count":13,"area":"mllm"},{"id":"2304.07633","title":"Interpretable Detection of Out-of-Context Misinformation with Neural-Symbolic-Enhanced Large Multimodal Model","created":"2023-04-15","cited_by_count":8,"area":"mllm"},{"id":"2502.10455","title":"E2LVLM:Evidence-Enhanced Large Vision-Language Model for Multimodal Out-of-Context Misinformation Detection","created":"2025-02-12","cited_by_count":7,"area":"mllm"},{"id":"2508.09999","title":"XFacta: Contemporary, Real-World Dataset and Evaluation for Multimodal Misinformation Detection with Multimodal LLMs","created":"2025-08-04","cited_by_count":7,"area":"mllm"},{"id":"2501.11403","title":"Verifying Cross-modal Entity Consistency in News using Vision-language Models","created":"2025-01-20","cited_by_count":5,"area":"mllm"},{"id":"2505.15489","title":"Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models","created":"2025-05-21","cited_by_count":5,"area":"mllm"},{"id":"2403.08776","title":"Leveraging Chat-Based Large Vision Language Models for Multimodal Out-Of-Context Detection","created":"2024-01-22","cited_by_count":4,"area":"mllm"},{"id":"2410.04426","title":"CoVLM: Leveraging Consensus from Vision-Language Models for Semi-supervised Multi-modal Fake News Detection","created":"2024-10-06","cited_by_count":0,"area":"mllm"},{"id":"2606.22339","title":"T-IMPACT: A Severity-Aware Benchmark for Contextual Image-Text Manipulation","created":"2026-06-21","cited_by_count":0,"area":"mllm"},{"id":"2609.01383","title":"InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations","created":"2026-09-01","cited_by_count":0,"area":"mllm"}],"next_cursor":null}