{"url":"/dataset/openchair","name":"OpenCHAIR","full_name":null,"description_markdown":"OpenCHAIR is a benchmark for evaluating open-vocabulary hallucinations in image captioning models. \r\nBy leveraging the linguistic knowledge of LLMs, OpenCHAIR is able to perform fine-grained hallucination measurements, as well as significantly increase the amount of objects that can be measured (especially when compared to the existing benchmark, CHAIR).\r\nTo exploit the LLM's full potential we construct a new dataset by generating 5000 captions with highly diverse objects and let a powerful text-to-image model generate images for them. We find that we are not just able to increase the benchmark's diversity, but also improve the evaluation accuracy with respect to CHAIR's.\r\n\r\nFor more info see https://assafbk.github.io/mocha/","description_withheld":null,"homepage":"https://huggingface.co/datasets/moranyanuka/OpenCHAIR","introduced_date":"2023-12-06","introduced_date_note":null,"introduced_by":{"paper":"/paper/mocha-multi-objective-reinforcement","title":"Mitigating Open-Vocabulary Caption Hallucinations","first_author":"Assaf Ben-Kish","url":null},"license":{"name":"apache-2.0","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["OpenCHAIR"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}