{"url":"/dataset/advglue","name":"AdvGLUE","full_name":"Adversarial GLUE","description_markdown":"Adversarial GLUE (AdvGLUE) is a new multi-task benchmark to quantitatively and thoroughly explore and evaluate the vulnerabilities of modern large-scale language models under various types of adversarial attacks. In particular, we systematically apply 14 textual adversarial attack methods to [GLUE](/dataset/glue) tasks to construct AdvGLUE, which is further validated by humans for reliable annotations.\r\n\r\nDescription from: [Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models](https://paperswithcode.com/paper/adversarial-glue-a-multi-task-benchmark-for)","description_withheld":null,"homepage":"https://adversarialglue.github.io/","introduced_date":"2021-11-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/adversarial-glue-a-multi-task-benchmark-for","title":"Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models","first_author":"Boxin Wang","url":null},"license":{"name":"CC BY-SA 4.0","url":"http://creativecommons.org/licenses/by-sa/4.0/legalcode"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Adversarial Robustness","url":"/task/adversarial-robustness","datasets_with_task":"/datasets/task/adversarial-robustness"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["AdvGLUE"],"data_loaders":[],"num_papers_in_archive":36,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/adversarial-robustness-on-advglue","task":"Adversarial Robustness","dataset_variant":"AdvGLUE","rows":10,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"DeBERTa (single model)","paper":"/paper/adversarial-glue-a-multi-task-benchmark-for","metrics":{"Accuracy":"0.6086"},"code_links":[{"title":"ai-secure/adversarial-glue","url":"https://github.com/ai-secure/adversarial-glue"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/adversarial-glue-a-multi-task-benchmark-for","title":"Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models","date":"2021-11-04","rows_on_this_dataset":10,"code_links":1,"syntology":null}],"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."}