{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/valse","name":"VALSE","full_name":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","description_markdown":"We propose VALSE (Vision And Language Structured Evaluation), a novel benchmark designed for testing general-purpose pretrained vision and language (V&L) models for their visio-linguistic grounding capabilities on specific linguistic phenomena. VALSE offers a suite of six tests covering various linguistic constructs. Solving these requires models to ground linguistic phenomena in the visual modality, allowing more fine-grained evaluations than hitherto possible.\r\nWe expect VALSE to serve as an important benchmark to measure future progress of pretrained V&L models from a linguistic perspective, complementing the canonical task-centred V&L evaluations.","description_withheld":null,"homepage":"https://github.com/Heidelberg-NLP/VALSE","introduced_date":"2021-12-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/valse-a-task-independent-benchmark-for-vision-1","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","first_author":"Letitia Parcalabescu","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"image-sentence alignment","url":"/task/image-sentence-alignment","datasets_with_task":"/datasets/task/image-sentence-alignment"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["VALSE foil-it (noun phrases)","VALSE coreference clean","VALSE coreference standard","VALSE actant swap","VALSE action replacement","VALSE spatial relations","VALSE counting adversarial","VALSE counting small numbers","VALSE counting balanced","VALSE plurality","VALSE existence","VALSE"],"data_loaders":[],"num_papers_in_archive":26,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-sentence-alignment-on-valse","task":"image-sentence alignment","dataset_variant":"VALSE","rows":7,"metrics":["average pairwise accuracy","Average Accuracy"],"first_row_in_archive_order":{"model":"ViLBERT 12-in-1","paper":"/paper/valse-a-task-independent-benchmark-for-vision-1","metrics":{"Average Accuracy":"63.2","average pairwise accuracy":"75.1"},"code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-sentence-alignment-on-valse-actant-swap","task":"image-sentence alignment","dataset_variant":"VALSE actant swap","rows":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"GPT2","paper":"/paper/valse-a-task-independent-benchmark-for-vision-1","metrics":{"pairwise accuracy":"76.9"},"code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-sentence-alignment-on-valse-action","task":"image-sentence alignment","dataset_variant":"VALSE action replacement","rows":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"CLIP","paper":"/paper/valse-a-task-independent-benchmark-for-vision-1","metrics":{"pairwise accuracy":"75.6"},"code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-sentence-alignment-on-valse-coreference","task":"image-sentence alignment","dataset_variant":"VALSE coreference standard","rows":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"ViLBERT 12-in-1","paper":"/paper/valse-a-task-independent-benchmark-for-vision-1","metrics":{"Accuracy (%)":"54.4","pairwise accuracy":"75.7"},"code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-sentence-alignment-on-valse-coreference-1","task":"image-sentence alignment","dataset_variant":"VALSE coreference clean","rows":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"ViLBERT 12-in-1","paper":"/paper/valse-a-task-independent-benchmark-for-vision-1","metrics":{"Accuracy (%)":"54.3","pairwise accuracy":"69.2"},"code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-sentence-alignment-on-valse-counting","task":"image-sentence alignment","dataset_variant":"VALSE counting balanced","rows":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"ViLBERT 12-in-1","paper":"/paper/valse-a-task-independent-benchmark-for-vision-1","metrics":{"Accuracy (%)":"64.9","pairwise accuracy":"76.7"},"code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-sentence-alignment-on-valse-counting-1","task":"image-sentence alignment","dataset_variant":"VALSE counting small numbers","rows":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"ViLBERT 12-in-1","paper":"/paper/valse-a-task-independent-benchmark-for-vision-1","metrics":{"Accuracy (%)":"69.2","pairwise accuracy":"80.2"},"code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-sentence-alignment-on-valse-counting-2","task":"image-sentence alignment","dataset_variant":"VALSE counting adversarial","rows":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"ViLBERT 12-in-1","paper":"/paper/valse-a-task-independent-benchmark-for-vision-1","metrics":{"Accuracy (%)":"66.7","pairwise accuracy":"77.3"},"code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-sentence-alignment-on-valse-existence","task":"image-sentence alignment","dataset_variant":"VALSE existence","rows":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"ViLBERT 12-in-1","paper":"/paper/valse-a-task-independent-benchmark-for-vision-1","metrics":{"Accuracy (%)":"89.0","pairwise accuracy":"95.6"},"code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-sentence-alignment-on-valse-foil-it","task":"image-sentence alignment","dataset_variant":"VALSE foil-it (noun phrases)","rows":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"CLIP","paper":"/paper/valse-a-task-independent-benchmark-for-vision-1","metrics":{"pairwise accuracy":"88.8"},"code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-sentence-alignment-on-valse-plurality","task":"image-sentence alignment","dataset_variant":"VALSE plurality","rows":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"ViLBERT 12-in-1","paper":"/paper/valse-a-task-independent-benchmark-for-vision-1","metrics":{"Accuracy (%)":"62.0","pairwise accuracy":"72.4"},"code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-sentence-alignment-on-valse-spatial","task":"image-sentence alignment","dataset_variant":"VALSE spatial relations","rows":7,"metrics":["pairwise accuracy","Accuracy (%)"],"first_row_in_archive_order":{"model":"GPT1","paper":"/paper/valse-a-task-independent-benchmark-for-vision-1","metrics":{"pairwise accuracy":"77.2"},"code_links":[{"title":"heidelberg-nlp/valse","url":"https://github.com/heidelberg-nlp/valse"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":1,"of":1,"counts":{"papers_with_a_benchmark_row":1,"with_a_code_link":1,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":1,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/valse-a-task-independent-benchmark-for-vision-1","slug":"valse-a-task-independent-benchmark-for-vision-1","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","date":"2021-12-14","arxiv_id":"2112.07566","rows_on_this_dataset":84,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":5,"official":{"repos":["heidelberg-nlp/valse"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/valse-a-task-independent-benchmark-for-vision-1#ran","syntology_url":"https://syntology.ai/paper/2112.07566","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.07566"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/valse-a-task-independent-benchmark-for-vision-1","slug":"valse-a-task-independent-benchmark-for-vision-1","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","date":"2021-12-14","arxiv_id":"2112.07566","rows_on_this_dataset":84,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":5,"official":{"repos":["heidelberg-nlp/valse"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/valse-a-task-independent-benchmark-for-vision-1#ran","syntology_url":"https://syntology.ai/paper/2112.07566","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.07566"}}}}],"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/dataset/valse/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/valse/papers/ran/1","json":"/dataset/valse/papers/ran/1.json","rows":1}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":1,"samples_harvested":9,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":5,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":1,"papers_with_a_run_with_no_instrument_failure":1,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"c12bf5b4a5e756f4072fbe0549693cc8a0bb4d5837c3fd039f28c25e0ee862ee","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}