MFC-Bench

MFC-Bench is a benchmark designed to evaluate the factual accuracy of large vision-language models (LVLMs) in multimodal fact-checking across three stages: Manipulation, Out-of-Context, and Veracity Classification.

Papers using MFC-Bench (3)

GeM-VG: Towards Generalized Multi-image Visual Grounding with Multimodal Large Language Models2026MFC-Bench: Benchmarking Multimodal Fact-Checking with Large Vision-Language Models2024MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs2024