サインイン
インサイト - Multimodal Fact-Checking
LRQ-Fact: A Framework for Multimodal Fact-Checking Using LLM-Generated Questions
Lrq-Fact is a novel automated framework that enhances multimodal fact-checking by using LLMs and VLMs to generate relevant questions about both the textual and visual content, improving detection accuracy and providing transparent rationales for its veracity assessments.
RED-DOT: Multimodal Fact-Checking with Relevant Evidence Detection
Introducing Relevant Evidence Detection in Multimodal Fact-Checking to improve accuracy and performance.