{"url":"/dataset/hallueditbench","name":"HalluEditBench","full_name":null,"description_markdown":"HalluEditBench is a comprehensive benchmark for evaluating knowledge editing methods' effectiveness in correcting real-world hallucinations. HalluEdit features a rigorously constructed dataset spanning nine domains and 26 topics. It evaluates methods across five dimensions: Efficacy, Generalization, Portability, Locality, and Robustness.","description_withheld":null,"homepage":"https://github.com/llm-editing/hallu-edit","introduced_date":"2024-10-21","introduced_date_note":null,"introduced_by":{"paper":"/paper/can-knowledge-editing-really-correct","title":"Can Knowledge Editing Really Correct Hallucinations?","first_author":"Baixiang Huang","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"knowledge editing","url":"/task/knowledge-editing","datasets_with_task":"/datasets/task/knowledge-editing"},{"name":"Hallucination Evaluation","url":"/task/hallucination-evaluation","datasets_with_task":"/datasets/task/hallucination-evaluation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["HalluEditBench"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/llm-editing/HalluEditBench","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":2,"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."}