Multimodal Fact-Checking with Vision Language Models: A Probing Classifier based Solution with Embedding Strategies. | AVESİS

Middle East Technical University Research Information System

Multimodal Fact-Checking with Vision Language Models: A Probing Classifier based Solution with Embedding Strategies.

Copy For Citation

Karagöz P., Çekinel R. F., Çöltekin Ç.

31st International Conference on Computational Linguistics (COLING), Abu Dhabi, United Arab Emirates, 19 - 24 January 2025, pp.4622-4633

Publication Type: Conference Paper / Full Text
City: Abu Dhabi
Country: United Arab Emirates
Page Numbers: pp.4622-4633
Middle East Technical University Affiliated: Yes