{"url":"/dataset/babyslm","name":"BabySLM","full_name":null,"description_markdown":"**BabySLM** is a language-acquisition-friendly benchmark to probe speech-based LMs at the lexical and syntactic levels, both of which are compatible with the vocabulary typical of children's language experiences.\r\n\r\nSource: [BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language models](https://arxiv.org/pdf/2306.01506v1.pdf)\r\n\r\nImage Source: [BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language models](https://arxiv.org/pdf/2306.01506v1.pdf)","description_withheld":null,"homepage":"https://github.com/MarvinLvn/BabySLM","introduced_date":"2023-06-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/babyslm-language-acquisition-friendly","title":"BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language models","first_author":"Marvin Lavechin","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Language Acquisition","url":"/task/language-acquisition","datasets_with_task":"/datasets/task/language-acquisition"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["BabySLM"],"data_loaders":[],"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."}