{"url":"/dataset/nolima","name":"NoLiMa","full_name":"NoLiMa: Long-Context Evaluation Beyond Literal Matching","description_markdown":"A benchmark extending needle-in-a-haystack (NIAH) test with a carefully designed needle set, where questions and needles have minimal lexical overlap, requiring models to infer latent associations to locate the needle within the haystack.","description_withheld":null,"homepage":"https://huggingface.co/datasets/amodaresi/NoLiMa","introduced_date":"2025-02-07","introduced_date_note":null,"introduced_by":{"paper":"/paper/nolima-long-context-evaluation-beyond-literal","title":"NoLiMa: Long-Context Evaluation Beyond Literal Matching","first_author":"Ali Modarressi","url":null},"license":null,"modalities":[],"tasks":[{"name":"Long-Context Understanding","url":"/task/long-context-understanding","datasets_with_task":"/datasets/task/long-context-understanding"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["NoLiMa"],"data_loaders":[],"num_papers_in_archive":1,"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":"2026-09-25T09:33:49+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."}