{"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/webquestionssp","name":"WebQuestionsSP","full_name":"WebQuestions Semantic Parses Dataset","description_markdown":"The WebQuestionsSP dataset is released as part of our ACL-2016 paper “The Value of Semantic Parse Labeling for Knowledge Base Question Answering” [Yih, Richardson, Meek, Chang & Suh, 2016], in which we evaluated the value of gathering semantic parses, vs. answers, for a set of questions that originally comes from WebQuestions [Berant et al., 2013]. The WebQuestionsSP dataset contains full semantic parses in SPARQL queries for 4,737 questions, and “partial” annotations for the remaining 1,073 questions for which a valid parse could not be formulated or where the question itself is bad or needs a descriptive answer. This release also includes an evaluation script and the output of the STAGG semantic parsing system when trained using the full semantic parses. More detail can be found in the document and labeling instructions included in this release, as well as the paper.\r\n\r\nSource: [WebQuestions Semantic Parses Dataset](https://www.microsoft.com/en-us/download/details.aspx?id=52763)","description_withheld":null,"homepage":"https://www.microsoft.com/en-us/download/details.aspx?id=52763","introduced_date":"2016-08-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-value-of-semantic-parse-labeling-for","title":"The Value of Semantic Parse Labeling for Knowledge Base Question Answering","first_author":"Wen-tau Yih","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Semantic Parsing","url":"/task/semantic-parsing","datasets_with_task":"/datasets/task/semantic-parsing"},{"name":"Entity Linking","url":"/task/entity-linking","datasets_with_task":"/datasets/task/entity-linking"},{"name":"Knowledge Base Question Answering","url":"/task/knowledge-base-question-answering","datasets_with_task":"/datasets/task/knowledge-base-question-answering"}],"languages":[],"variants":["WebQSP-WD","WebQuestionsSP"],"data_loaders":[],"num_papers_in_archive":61,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/knowledge-base-question-answering-on-1","task":"Knowledge Base Question Answering","dataset_variant":"WebQuestionsSP","rows":8,"metrics":["Hits@1","F1","Accuracy"],"first_row_in_archive_order":{"model":"ChatKBQA","paper":"/paper/chatkbqa-a-generate-then-retrieve-framework","metrics":{"Accuracy":"77.8","F1":"83.5","Hits@1":"86.4"},"code_links":[{"title":"lhrlab/chatkbqa","url":"https://github.com/lhrlab/chatkbqa"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/semantic-parsing-on-webquestionssp","task":"Semantic Parsing","dataset_variant":"WebQuestionsSP","rows":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ReaRev","paper":"/paper/rearev-adaptive-reasoning-for-question","metrics":{"Accuracy":"76.4"},"code_links":[{"title":"cmavro/rearev_kgqa","url":"https://github.com/cmavro/rearev_kgqa"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-answering-on-webquestionssp","task":"Question Answering","dataset_variant":"WebQuestionsSP","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ChatGPT","paper":"/paper/evaluation-of-chatgpt-as-a-question-answering","metrics":{"Accuracy":"83.7"},"code_links":[{"title":"tan92hl/complex-question-answering-evaluation-of-gpt-family","url":"https://github.com/tan92hl/complex-question-answering-evaluation-of-gpt-family"},{"title":"tan92hl/complex-question-answering-evaluation-of-chatgpt","url":"https://github.com/tan92hl/complex-question-answering-evaluation-of-chatgpt"}]},"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":12,"of":12,"counts":{"papers_with_a_benchmark_row":12,"with_a_code_link":10,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":12,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/sparkle-enhancing-sparql-generation-with","slug":"sparkle-enhancing-sparql-generation-with","title":"SPARKLE: Enhancing SPARQL Generation with Direct KG Integration in Decoding","date":"2024-06-29","arxiv_id":"2407.01626","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/understand-what-llm-needs-dual-preference","slug":"understand-what-llm-needs-dual-preference","title":"Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation","date":"2024-06-26","arxiv_id":"2406.18676","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["dongguanting/dpa-rag"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/understand-what-llm-needs-dual-preference#ran","syntology_url":"https://syntology.ai/paper/2406.18676","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18676"}}}},{"paper":"/paper/chatkbqa-a-generate-then-retrieve-framework","slug":"chatkbqa-a-generate-then-retrieve-framework","title":"ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models","date":"2023-10-13","arxiv_id":"2310.08975","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":4,"samples_unverified":5,"pointer_only_for_licence":4,"official":{"repos":["lhrlab/chatkbqa"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/chatkbqa-a-generate-then-retrieve-framework#ran","syntology_url":"https://syntology.ai/paper/2310.08975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08975"}}}},{"paper":"/paper/bridging-the-kb-text-gap-leveraging","slug":"bridging-the-kb-text-gap-leveraging","title":"Bridging the KB-Text Gap: Leveraging Structured Knowledge-aware Pre-training for KBQA","date":"2023-08-28","arxiv_id":"2308.14436","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":10,"official":{"repos":["dongguanting/skp-for-kbqa"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bridging-the-kb-text-gap-leveraging#ran","syntology_url":"https://syntology.ai/paper/2308.14436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.14436"}}}},{"paper":"/paper/evaluation-of-chatgpt-as-a-question-answering","slug":"evaluation-of-chatgpt-as-a-question-answering","title":"Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family","date":"2023-03-14","arxiv_id":"2303.07992","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/rearev-adaptive-reasoning-for-question","slug":"rearev-adaptive-reasoning-for-question","title":"ReaRev: Adaptive Reasoning for Question Answering over Knowledge Graphs","date":"2022-10-24","arxiv_id":"2210.13650","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/retrack-a-flexible-and-efficient-framework","slug":"retrack-a-flexible-and-efficient-framework","title":"ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering","date":"2021-08-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/case-based-reasoning-for-natural-language","slug":"case-based-reasoning-for-natural-language","title":"Case-based Reasoning for Natural Language Queries over Knowledge Bases","date":"2021-04-18","arxiv_id":"2104.08762","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/improving-multi-hop-knowledge-base-question","slug":"improving-multi-hop-knowledge-base-question","title":"Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals","date":"2021-01-11","arxiv_id":"2101.03737","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unified-open-domain-question-answering-with","slug":"unified-open-domain-question-answering-with","title":"UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering","date":"2020-12-29","arxiv_id":"2012.14610","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/exploring-the-limits-of-transfer-learning","slug":"exploring-the-limits-of-transfer-learning","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","date":"2019-10-23","arxiv_id":"1910.10683","rows_on_this_dataset":1,"code_links":57,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":31,"samples_ran":21,"samples_constructed":0,"samples_ran_checked":20,"samples_ran_instrument_failed":1,"samples_unverified":10,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/exploring-the-limits-of-transfer-learning#ran","syntology_url":"https://syntology.ai/paper/1910.10683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.10683"}}}},{"paper":"/paper/the-value-of-semantic-parse-labeling-for","slug":"the-value-of-semantic-parse-labeling-for","title":"The Value of Semantic Parse Labeling for Knowledge Base Question Answering","date":"2016-08-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/sparkle-enhancing-sparql-generation-with","slug":"sparkle-enhancing-sparql-generation-with","title":"SPARKLE: Enhancing SPARQL Generation with Direct KG Integration in Decoding","date":"2024-06-29","arxiv_id":"2407.01626","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/understand-what-llm-needs-dual-preference","slug":"understand-what-llm-needs-dual-preference","title":"Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation","date":"2024-06-26","arxiv_id":"2406.18676","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["dongguanting/dpa-rag"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/understand-what-llm-needs-dual-preference#ran","syntology_url":"https://syntology.ai/paper/2406.18676","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18676"}}}},{"paper":"/paper/chatkbqa-a-generate-then-retrieve-framework","slug":"chatkbqa-a-generate-then-retrieve-framework","title":"ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models","date":"2023-10-13","arxiv_id":"2310.08975","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":4,"samples_unverified":5,"pointer_only_for_licence":4,"official":{"repos":["lhrlab/chatkbqa"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/chatkbqa-a-generate-then-retrieve-framework#ran","syntology_url":"https://syntology.ai/paper/2310.08975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08975"}}}},{"paper":"/paper/bridging-the-kb-text-gap-leveraging","slug":"bridging-the-kb-text-gap-leveraging","title":"Bridging the KB-Text Gap: Leveraging Structured Knowledge-aware Pre-training for KBQA","date":"2023-08-28","arxiv_id":"2308.14436","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":10,"official":{"repos":["dongguanting/skp-for-kbqa"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bridging-the-kb-text-gap-leveraging#ran","syntology_url":"https://syntology.ai/paper/2308.14436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.14436"}}}},{"paper":"/paper/evaluation-of-chatgpt-as-a-question-answering","slug":"evaluation-of-chatgpt-as-a-question-answering","title":"Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family","date":"2023-03-14","arxiv_id":"2303.07992","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/rearev-adaptive-reasoning-for-question","slug":"rearev-adaptive-reasoning-for-question","title":"ReaRev: Adaptive Reasoning for Question Answering over Knowledge Graphs","date":"2022-10-24","arxiv_id":"2210.13650","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/retrack-a-flexible-and-efficient-framework","slug":"retrack-a-flexible-and-efficient-framework","title":"ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering","date":"2021-08-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/case-based-reasoning-for-natural-language","slug":"case-based-reasoning-for-natural-language","title":"Case-based Reasoning for Natural Language Queries over Knowledge Bases","date":"2021-04-18","arxiv_id":"2104.08762","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/improving-multi-hop-knowledge-base-question","slug":"improving-multi-hop-knowledge-base-question","title":"Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals","date":"2021-01-11","arxiv_id":"2101.03737","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unified-open-domain-question-answering-with","slug":"unified-open-domain-question-answering-with","title":"UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering","date":"2020-12-29","arxiv_id":"2012.14610","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/exploring-the-limits-of-transfer-learning","slug":"exploring-the-limits-of-transfer-learning","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","date":"2019-10-23","arxiv_id":"1910.10683","rows_on_this_dataset":1,"code_links":57,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":31,"samples_ran":21,"samples_constructed":0,"samples_ran_checked":20,"samples_ran_instrument_failed":1,"samples_unverified":10,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/exploring-the-limits-of-transfer-learning#ran","syntology_url":"https://syntology.ai/paper/1910.10683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.10683"}}}},{"paper":"/paper/the-value-of-semantic-parse-labeling-for","slug":"the-value-of-semantic-parse-labeling-for","title":"The Value of Semantic Parse Labeling for Knowledge Base Question Answering","date":"2016-08-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null}],"papers_where_code_ran":4,"papers_where_code_ran_first_page":"/dataset/webquestionssp/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/webquestionssp/papers/ran/1","json":"/dataset/webquestionssp/papers/ran/1.json","rows":4}],"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":4,"samples_harvested":60,"samples_ran":43,"samples_constructed":0,"samples_ran_checked":37,"samples_ran_instrument_failed":6,"samples_unverified":17,"pointer_only_for_licence":17,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":4,"papers_with_a_run_with_no_instrument_failure":3,"papers_where_every_run_was_an_instrument_failure":1,"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":"259774f4598a8c4931e849208dc85a43bad99fce0cffb4be46fcb53a036eff9c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}