{"url":"/dataset/aci-bench","name":"ACI-Bench","full_name":null,"description_markdown":"Aci-bench: a Novel Ambient Clinical Intelligence Dataset for Benchmarking Automatic Visit Note Generation","description_withheld":null,"homepage":"https://github.com/wyim/aci-bench","introduced_date":"2023-06-03","introduced_date_note":null,"introduced_by":{"paper":"/paper/aci-bench-a-novel-ambient-clinical","title":"ACI-BENCH: a Novel Ambient Clinical Intelligence Dataset for Benchmarking Automatic Visit Note Generation","first_author":"Wen-wai Yim","url":null},"license":null,"modalities":[],"tasks":[{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"}],"languages":[],"variants":["ACI-Bench"],"data_loaders":[],"num_papers_in_archive":8,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-summarization-on-aci-bench","task":"Text Summarization","dataset_variant":"ACI-Bench","rows":1,"metrics":["ROUGE-1","ROUGE-2","ROUGE-L"],"first_row_in_archive_order":{"model":"CriSPO 3-shot","paper":"/paper/crispo-multi-aspect-critique-suggestion","metrics":{"ROUGE-1":"63.1","ROUGE-2":"32.5","ROUGE-L":"41"},"code_links":[{"title":"amazon-science/crispo","url":"https://github.com/amazon-science/crispo"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/crispo-multi-aspect-critique-suggestion","title":"CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text Generation","date":"2024-10-03","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"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."}