{"url":"/dataset/clinc150","name":"CLINC150","full_name":"CLINC150","description_markdown":"This dataset is for evaluating the performance of intent classification systems in the presence of \"out-of-scope\" queries, i.e., queries that do not fall into any of the system-supported intent classes. The dataset includes both in-scope and out-of-scope data.\r\n\r\nSource: [CLINC150](https://github.com/clinc/oos-eval)","description_withheld":null,"homepage":"https://github.com/clinc/oos-eval","introduced_date":"2019-09-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/an-evaluation-dataset-for-intent","title":"An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction","first_author":"Stefan Larson","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Intent Detection","url":"/task/intent-detection","datasets_with_task":"/datasets/task/intent-detection"},{"name":"Open Intent Discovery","url":"/task/open-intent-discovery","datasets_with_task":"/datasets/task/open-intent-discovery"},{"name":"Intent Classification","url":"/task/intent-classification","datasets_with_task":"/datasets/task/intent-classification"}],"languages":[],"variants":["CLINC150","clinc_oos","CLINC150 5-shot","CLINC150 10-shot"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/clinc/clinc_oos","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/clinc_oos","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/clinc_oos","frameworks":["tf","jax"]},{"repo":"https://github.com/clinc/oos-eval","url":"https://github.com/clinc/oos-eval","frameworks":[]}],"num_papers_in_archive":87,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/open-intent-discovery-on-clinc150","task":"Open Intent Discovery","dataset_variant":"CLINC150","rows":2,"metrics":["ACC","ARI","NMI"],"first_row_in_archive_order":{"model":"DSSCC","paper":"/paper/intent-detection-and-discovery-from-user-logs","metrics":{"ACC":"87.91","ARI":"0.8109","NMI":"0.9387"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/intent-detection-on-clinc150","task":"Intent Detection","dataset_variant":"CLINC150","rows":1,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"RoBERTa-Large + ICDA","paper":"/paper/selective-in-context-data-augmentation-for","metrics":{"Accuracy (%)":"97.12"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/intent-detection-on-clinc150-10-shot","task":"Intent Detection","dataset_variant":"CLINC150 10-shot","rows":1,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"RoBERTa-Large + ICDA","paper":"/paper/selective-in-context-data-augmentation-for","metrics":{"Accuracy (%)":"94.84"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/intent-detection-on-clinc150-5-shot","task":"Intent Detection","dataset_variant":"CLINC150 5-shot","rows":1,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"RoBERTa-Large + ICDA","paper":"/paper/selective-in-context-data-augmentation-for","metrics":{"Accuracy (%)":"92.62"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-classification-on-clinc-oos","task":"Text Classification","dataset_variant":"clinc_oos","rows":0,"metrics":["Accuracy","F1 Macro","F1 Micro","F1 Weighted","Precision Macro","Precision Micro","Precision Weighted","Recall Macro","Recall Micro","Recall Weighted","loss"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/selective-in-context-data-augmentation-for","title":"Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information","date":"2023-02-10","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/intent-detection-and-discovery-from-user-logs","title":"Intent Detection and Discovery from User Logs via Deep Semi-Supervised Contrastive Clustering","date":"2022-07-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/discovering-new-intents-with-deep-aligned","title":"Discovering New Intents with Deep Aligned Clustering","date":"2020-12-16","rows_on_this_dataset":1,"code_links":2,"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."}