Search Results for author:
Found 1 papers, 0 papers with code
ALOHa: A New Measure for Hallucination in Captioning Models
Despite recent advances in multimodal pre-training for visual description, state-of-the-art models still produce captions containing errors, such as hallucinating objects not present in a scene.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
