{"url":"/dataset/dialogstudio","name":"DialogStudio","full_name":null,"description_markdown":"DialogStudio, a meticulously curated collection of dialogue datasets. These datasets are unified under a consistent format while retaining their original information. We incorporate domain-aware prompts and identify dataset licenses, making DialogStudio an exceptionally rich and diverse resource for dialogue research and model training.","description_withheld":null,"homepage":"https://github.com/salesforce/DialogStudio","introduced_date":"2023-07-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/dialogstudio-towards-richest-and-most-diverse","title":"DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI","first_author":"JianGuo Zhang","url":null},"license":{"name":"Apache License 2.0","url":"https://www.apache.org/licenses/LICENSE-2.0"},"modalities":[],"tasks":[],"languages":[],"variants":["DialogStudio"],"data_loaders":[],"num_papers_in_archive":6,"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."}