{"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":"/task/knowledge-base-question-answering","name":"Knowledge Base Question Answering","slug":"knowledge-base-question-answering","description_markdown":"Knowledge Base Q&A is the task of answering questions from a knowledge base.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering](https://www.aclweb.org/anthology/C18-1280.pdf) )</span>","categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":136,"papers_with_code":67,"benchmarks":10,"benchmark_tables_in_archive":10,"benchmark_tables_shown":10,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":15,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/knowledge-base-question-answering-on-qald-9","slug":"knowledge-base-question-answering-on-qald-9","dataset":"QALD-9-Plus","dataset_url":"/dataset/qald-9-plus","rows_in_archive":12,"metrics":["Macro F1"],"first_row_in_archive_order":{"model":"QAnswer-Wikidata-English","paper_title":"QALD-9-plus: A Multilingual Dataset for Question Answering over DBpedia and Wikidata Translated by Native Speakers","paper_url":"/paper/qald-9-plus-a-multilingual-dataset-for","paper_date":"2022-01-31","arxiv_id":"2202.00120","code_links":[{"title":"perevalov/qald_9_plus","url":"https://github.com/perevalov/qald_9_plus"}],"syntology":null}},{"leaderboard":"/sota/knowledge-base-question-answering-on-1","slug":"knowledge-base-question-answering-on-1","dataset":"WebQuestionsSP","dataset_url":"/dataset/webquestionssp","rows_in_archive":8,"metrics":["Hits@1","F1","Accuracy"],"first_row_in_archive_order":{"model":"ChatKBQA","paper_title":"ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models","paper_url":"/paper/chatkbqa-a-generate-then-retrieve-framework","paper_date":"2023-10-13","arxiv_id":"2310.08975","code_links":[{"title":"lhrlab/chatkbqa","url":"https://github.com/lhrlab/chatkbqa"}],"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":5,"n_honours":2,"n_violates":1,"n_no_contract":4,"n_pointer_only":4,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","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"}},"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"]}}}},{"leaderboard":"/sota/knowledge-base-question-answering-on-lc-quad","slug":"knowledge-base-question-answering-on-lc-quad","dataset":"LC-QuAD 1.0","dataset_url":"/dataset/lc-quad-2-0","rows_in_archive":7,"metrics":["F1"],"first_row_in_archive_order":{"model":"HGNet (oracle entity used)","paper_title":"Outlining and Filling: Hierarchical Query Graph Generation for Answering Complex Questions over Knowledge Graphs","paper_url":"/paper/outlining-and-filling-hierarchical-query","paper_date":"2021-11-01","arxiv_id":"2111.00732","code_links":[{"title":"bahuia/aqgnet","url":"https://github.com/bahuia/aqgnet"},{"title":"bahuia/hgnet","url":"https://github.com/bahuia/hgnet"}],"syntology":null}},{"leaderboard":"/sota/knowledge-base-question-answering-on","slug":"knowledge-base-question-answering-on","dataset":"ComplexWebQuestions","dataset_url":"/dataset/complexwebquestions","rows_in_archive":6,"metrics":["Accuracy","F1","Hits@1","EM"],"first_row_in_archive_order":{"model":"ChatKBQA","paper_title":"ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models","paper_url":"/paper/chatkbqa-a-generate-then-retrieve-framework","paper_date":"2023-10-13","arxiv_id":"2310.08975","code_links":[{"title":"lhrlab/chatkbqa","url":"https://github.com/lhrlab/chatkbqa"}],"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":5,"n_honours":2,"n_violates":1,"n_no_contract":4,"n_pointer_only":4,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","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"}},"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"]}}}},{"leaderboard":"/sota/knowledge-base-question-answering-on-4","slug":"knowledge-base-question-answering-on-4","dataset":"SimpleQuestionsWikiData","dataset_url":"/dataset/simplequestionswikidata","rows_in_archive":5,"metrics":["F1"],"first_row_in_archive_order":{"model":"SPARKLE","paper_title":"SPARKLE: Enhancing SPARQL Generation with Direct KG Integration in Decoding","paper_url":"/paper/sparkle-enhancing-sparql-generation-with","paper_date":"2024-06-29","arxiv_id":"2407.01626","code_links":[{"title":"zzaebok/sparkle","url":"https://github.com/zzaebok/sparkle"}],"syntology":null}},{"leaderboard":"/sota/knowledge-base-question-answering-on-grailqa","slug":"knowledge-base-question-answering-on-grailqa","dataset":"GrailQA","dataset_url":"/dataset/grailqa","rows_in_archive":2,"metrics":["Compositional EM","Compositional F1","EM","I.I.D. EM","I.I.D. F1","Overall EM","Overall F1","Zero-shot EM","Zero-shot F1"],"first_row_in_archive_order":{"model":"ReTraCk","paper_title":"ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering","paper_url":"/paper/retrack-a-flexible-and-efficient-framework","paper_date":"2021-08-01","arxiv_id":null,"code_links":[{"title":"microsoft/KC","url":"https://github.com/microsoft/KC/tree/main/papers/ReTraCk"}],"syntology":null}},{"leaderboard":"/sota/knowledge-base-question-answering-on-2","slug":"knowledge-base-question-answering-on-2","dataset":"SimpleQuestions","dataset_url":"/dataset/simplequestions","rows_in_archive":1,"metrics":["EM"],"first_row_in_archive_order":{"model":"PoG-GPT4 (Tan et al., 2024)","paper_title":"Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning","paper_url":"/paper/paths-over-graph-knowledge-graph-enpowered","paper_date":"2024-10-18","arxiv_id":"2410.14211","code_links":[{"title":"SteveTANTAN/PoG","url":"https://github.com/SteveTANTAN/PoG"}],"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/paths-over-graph-knowledge-graph-enpowered#ran","syntology_url":"https://syntology.ai/paper/2410.14211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14211"}},"official":null}}},{"leaderboard":"/sota/knowledge-base-question-answering-on-3","slug":"knowledge-base-question-answering-on-3","dataset":"WebQuestions","dataset_url":"/dataset/webquestions","rows_in_archive":1,"metrics":["EM"],"first_row_in_archive_order":{"model":"PoG-GPT4 (Tan et al., 2024)","paper_title":"Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning","paper_url":"/paper/paths-over-graph-knowledge-graph-enpowered","paper_date":"2024-10-18","arxiv_id":"2410.14211","code_links":[{"title":"SteveTANTAN/PoG","url":"https://github.com/SteveTANTAN/PoG"}],"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/paths-over-graph-knowledge-graph-enpowered#ran","syntology_url":"https://syntology.ai/paper/2410.14211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14211"}},"official":null}}},{"leaderboard":"/sota/knowledge-base-question-answering-on-webqsp","slug":"knowledge-base-question-answering-on-webqsp","dataset":"WebQSP-WD","dataset_url":"/dataset/webqsp","rows_in_archive":1,"metrics":["Avg F1"],"first_row_in_archive_order":{"model":"GGNN","paper_title":"Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering","paper_url":"/paper/modeling-semantics-with-gated-graph-neural","paper_date":"2018-08-13","arxiv_id":"1808.04126","code_links":[{"title":"UKPLab/coling2018-graph-neural-networks-question-answering","url":"https://github.com/UKPLab/coling2018-graph-neural-networks-question-answering"}],"syntology":null}},{"leaderboard":"/sota/knowledge-base-question-answering-on-webqsp-1","slug":"knowledge-base-question-answering-on-webqsp-1","dataset":"WebQSP","dataset_url":"/dataset/webqsp","rows_in_archive":1,"metrics":["EM"],"first_row_in_archive_order":{"model":"PoG-GPT4 (Tan et al., 2024)","paper_title":"Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning","paper_url":"/paper/paths-over-graph-knowledge-graph-enpowered","paper_date":"2024-10-18","arxiv_id":"2410.14211","code_links":[{"title":"SteveTANTAN/PoG","url":"https://github.com/SteveTANTAN/PoG"}],"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/paths-over-graph-knowledge-graph-enpowered#ran","syntology_url":"https://syntology.ai/paper/2410.14211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14211"}},"official":null}}}],"datasets":[{"url":"/dataset/webquestions","name":"WebQuestions","full_name":"","num_papers_in_archive":241},{"url":"/dataset/simplequestions","name":"SimpleQuestions","full_name":"","num_papers_in_archive":120},{"url":"/dataset/complexwebquestions","name":"ComplexWebQuestions","full_name":"ComplexWebQuestions","num_papers_in_archive":62},{"url":"/dataset/webquestionssp","name":"WebQuestionsSP","full_name":"WebQuestions Semantic Parses Dataset","num_papers_in_archive":61},{"url":"/dataset/grailqa","name":"GrailQA","full_name":"Strongly Generalizable Question Answering","num_papers_in_archive":34},{"url":"/dataset/lc-quad-2-0","name":"LC-QuAD","full_name":"Largescale Complex Question Answering Dataset","num_papers_in_archive":10},{"url":"/dataset/rubq","name":"RuBQ","full_name":"Russian Knowledge Base Questions","num_papers_in_archive":7},{"url":"/dataset/frenchmedmcqa","name":"FrenchMedMCQA","full_name":"FrenchMedMCQA: A French Multiple-Choice Question Answering Dataset for Medical domain","num_papers_in_archive":6},{"url":"/dataset/simplequestionswikidata","name":"SimpleQuestionsWikiData","full_name":"","num_papers_in_archive":6},{"url":"/dataset/paraqa","name":"ParaQA","full_name":"","num_papers_in_archive":5},{"url":"/dataset/webqsp","name":"WebQSP","full_name":null,"num_papers_in_archive":5},{"url":"/dataset/vanilla","name":"VANiLLa","full_name":"","num_papers_in_archive":4},{"url":"/dataset/qald-9-plus","name":"QALD-9-Plus","full_name":"","num_papers_in_archive":3},{"url":"/dataset/geoquestions1089","name":"GeoQuestions1089","full_name":"","num_papers_in_archive":1},{"url":"/dataset/orkg-qa","name":"ORKG-QA","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/question-answering","name":"Question Answering"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":136,"of_with_code":67,"tagged_in_all":136,"counts":{"archive_papers_tagged":136,"with_a_code_link":67,"where_syntology_ran_a_sample":16,"not_listed_spam_title":0,"listed":136,"listed_where_code_ran":16,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":10,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":10,"listed_every_run_a_failure_of_syntologys_instrument":6,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/spinach-sparql-based-information-navigation","slug":"spinach-sparql-based-information-navigation","title":"SPINACH: SPARQL-Based Information Navigation for Challenging Real-World Questions","date":"2024-07-16","arxiv_id":"2407.11417","repositories_listed":2,"syntology":null},{"url":"/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","repositories_listed":2,"syntology":null},{"url":"/paper/don-t-generate-discriminate-a-proposal-for","slug":"don-t-generate-discriminate-a-proposal-for","title":"Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments","date":"2022-12-19","arxiv_id":"2212.09736","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/don-t-generate-discriminate-a-proposal-for#ran","syntology_url":"https://syntology.ai/paper/2212.09736","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09736"}},"official":{"repos":["dki-lab/pangu"],"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"]}}},{"url":"/paper/outlining-and-filling-hierarchical-query","slug":"outlining-and-filling-hierarchical-query","title":"Outlining and Filling: Hierarchical Query Graph Generation for Answering Complex Questions over Knowledge Graphs","date":"2021-11-01","arxiv_id":"2111.00732","repositories_listed":2,"syntology":null},{"url":"/paper/kagnet-knowledge-aware-graph-networks-for","slug":"kagnet-knowledge-aware-graph-networks-for","title":"KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning","date":"2019-09-04","arxiv_id":"1909.02151","repositories_listed":2,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/kagnet-knowledge-aware-graph-networks-for#ran","syntology_url":"https://syntology.ai/paper/1909.02151","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02151"}},"official":{"repos":["INK-USC/KagNet"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bidirectional-attentive-memory-networks-for","slug":"bidirectional-attentive-memory-networks-for","title":"Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases","date":"2019-03-06","arxiv_id":"1903.02188","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/bidirectional-attentive-memory-networks-for#ran","syntology_url":"https://syntology.ai/paper/1903.02188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.02188"}},"official":{"repos":["hugochan/BAMnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/multi-task-learning-with-multi-view-attention","slug":"multi-task-learning-with-multi-view-attention","title":"Multi-Task Learning with Multi-View Attention for Answer Selection and Knowledge Base Question Answering","date":"2018-12-06","arxiv_id":"1812.02354","repositories_listed":2,"syntology":null},{"url":"/paper/beyond-seen-data-improving-kbqa","slug":"beyond-seen-data-improving-kbqa","title":"Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation","date":"2025-02-18","arxiv_id":"2502.12737","repositories_listed":1,"syntology":null},{"url":"/paper/kbqa-o1-agentic-knowledge-base-question","slug":"kbqa-o1-agentic-knowledge-base-question","title":"KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search","date":"2025-01-31","arxiv_id":"2501.18922","repositories_listed":1,"syntology":{"n":8,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/kbqa-o1-agentic-knowledge-base-question#ran","syntology_url":"https://syntology.ai/paper/2501.18922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.18922"}},"official":{"repos":["lhrlab/kbqa-o1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/cypherbench-towards-precise-retrieval-over","slug":"cypherbench-towards-precise-retrieval-over","title":"CypherBench: Towards Precise Retrieval over Full-scale Modern Knowledge Graphs in the LLM Era","date":"2024-12-24","arxiv_id":"2412.18702","repositories_listed":1,"syntology":null},{"url":"/paper/paths-over-graph-knowledge-graph-enpowered","slug":"paths-over-graph-knowledge-graph-enpowered","title":"Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning","date":"2024-10-18","arxiv_id":"2410.14211","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/paths-over-graph-knowledge-graph-enpowered#ran","syntology_url":"https://syntology.ai/paper/2410.14211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14211"}},"official":null}},{"url":"/paper/semantic-parsing-with-candidate-expressions","slug":"semantic-parsing-with-candidate-expressions","title":"Semantic Parsing with Candidate Expressions for Knowledge Base Question Answering","date":"2024-10-01","arxiv_id":"2410.00414","repositories_listed":1,"syntology":null},{"url":"/paper/2408-02337","slug":"2408-02337","title":"Developing PUGG for Polish: A Modern Approach to KBQA, MRC, and IR Dataset Construction","date":"2024-08-05","arxiv_id":"2408.02337","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}},{"url":"/paper/retinaqa-a-knowledge-base-question-answering","slug":"retinaqa-a-knowledge-base-question-answering","title":"RetinaQA: A Robust Knowledge Base Question Answering Model for both Answerable and Unanswerable Questions","date":"2024-03-16","arxiv_id":"2403.10849","repositories_listed":1,"syntology":null},{"url":"/paper/interactive-kbqa-multi-turn-interactions-for","slug":"interactive-kbqa-multi-turn-interactions-for","title":"Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Models","date":"2024-02-23","arxiv_id":"2402.15131","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":3,"n_ran_checked":3,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":10,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/interactive-kbqa-multi-turn-interactions-for#ran","syntology_url":"https://syntology.ai/paper/2402.15131","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15131"}},"official":{"repos":["jimxionggm/interactive-kbqa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/triad-a-framework-leveraging-a-multi-role-llm","slug":"triad-a-framework-leveraging-a-multi-role-llm","title":"Triad: A Framework Leveraging a Multi-Role LLM-based Agent to Solve Knowledge Base Question Answering","date":"2024-02-22","arxiv_id":"2402.14320","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/triad-a-framework-leveraging-a-multi-role-llm#ran","syntology_url":"https://syntology.ai/paper/2402.14320","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14320"}},"official":{"repos":["ZJU-DCDLab/Triad"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/clue-guided-path-exploration-an-efficient","slug":"clue-guided-path-exploration-an-efficient","title":"Fine-Grained Stateful Knowledge Exploration: A Novel Paradigm for Integrating Knowledge Graphs with Large Language Models","date":"2024-01-24","arxiv_id":"2401.13444","repositories_listed":1,"syntology":null},{"url":"/paper/relation-aware-question-answering-for","slug":"relation-aware-question-answering-for","title":"Relation-Aware Question Answering for Heterogeneous Knowledge Graphs","date":"2023-12-19","arxiv_id":"2312.11922","repositories_listed":1,"syntology":null},{"url":"/paper/combining-transfer-learning-with-in-context","slug":"combining-transfer-learning-with-in-context","title":"Few-shot Transfer Learning for Knowledge Base Question Answering: Fusing Supervised Models with In-Context Learning","date":"2023-11-15","arxiv_id":"2311.08894","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-geospatial-question-answering","slug":"benchmarking-geospatial-question-answering","title":"Benchmarking Geospatial Question Answering Engines using the Dataset GeoQuestions1089","date":"2023-11-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":5,"n_honours":2,"n_violates":1,"n_no_contract":4,"n_pointer_only":4,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","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"}},"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"]}}},{"url":"/paper/data-distribution-bottlenecks-in-grounding","slug":"data-distribution-bottlenecks-in-grounding","title":"Data Distribution Bottlenecks in Grounding Language Models to Knowledge Bases","date":"2023-09-15","arxiv_id":"2309.08345","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","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"}},"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"]}}},{"url":"/paper/flexkbqa-a-flexible-llm-powered-framework-for","slug":"flexkbqa-a-flexible-llm-powered-framework-for","title":"FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering","date":"2023-08-23","arxiv_id":"2308.12060","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/flexkbqa-a-flexible-llm-powered-framework-for#ran","syntology_url":"https://syntology.ai/paper/2308.12060","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12060"}},"official":{"repos":["leezythu/flexkbqa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/question-answering-over-linked-data-with-gpt","slug":"question-answering-over-linked-data-with-gpt","title":"Question Answering over Linked Data with GPT-3","date":"2023-08-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/question-decomposition-tree-for-answering","slug":"question-decomposition-tree-for-answering","title":"Question Decomposition Tree for Answering Complex Questions over Knowledge Bases","date":"2023-06-13","arxiv_id":"2306.07597","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-base-question-answering-for-space","slug":"knowledge-base-question-answering-for-space","title":"Knowledge Base Question Answering for Space Debris Queries","date":"2023-05-31","arxiv_id":"2305.19734","repositories_listed":1,"syntology":null},{"url":"/paper/complementing-gpt-3-with-few-shot-sequence-to","slug":"complementing-gpt-3-with-few-shot-sequence-to","title":"Fine-tuned LLMs Know More, Hallucinate Less with Few-Shot Sequence-to-Sequence Semantic Parsing over Wikidata","date":"2023-05-23","arxiv_id":"2305.14202","repositories_listed":1,"syntology":null},{"url":"/paper/srtk-a-toolkit-for-semantic-relevant-subgraph","slug":"srtk-a-toolkit-for-semantic-relevant-subgraph","title":"SRTK: A Toolkit for Semantic-relevant Subgraph Retrieval","date":"2023-05-06","arxiv_id":"2305.04101","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-in-context-learning-for-knowledge","slug":"few-shot-in-context-learning-for-knowledge","title":"Few-shot In-context Learning for Knowledge Base Question Answering","date":"2023-05-02","arxiv_id":"2305.01750","repositories_listed":1,"syntology":{"n":16,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/few-shot-in-context-learning-for-knowledge#ran","syntology_url":"https://syntology.ai/paper/2305.01750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.01750"}},"official":{"repos":["ltl3a87/kb-binder"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/gett-qa-graph-embedding-based-t2t-transformer","slug":"gett-qa-graph-embedding-based-t2t-transformer","title":"GETT-QA: Graph Embedding based T2T Transformer for Knowledge Graph Question Answering","date":"2023-03-23","arxiv_id":"2303.13284","repositories_listed":1,"syntology":null},{"url":"/paper/a-universal-question-answering-platform-for","slug":"a-universal-question-answering-platform-for","title":"A Universal Question-Answering Platform for Knowledge Graphs","date":"2023-03-01","arxiv_id":"2303.00595","repositories_listed":1,"syntology":null},{"url":"/paper/improving-complex-knowledge-base-question","slug":"improving-complex-knowledge-base-question","title":"Improving Complex Knowledge Base Question Answering via Question-to-Action and Question-to-Question Alignment","date":"2022-12-26","arxiv_id":"2212.13036","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/improving-complex-knowledge-base-question#ran","syntology_url":"https://syntology.ai/paper/2212.13036","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.13036"}},"official":{"repos":["tttttttty/alcqa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/a-sequential-flow-control-framework-for-multi","slug":"a-sequential-flow-control-framework-for-multi","title":"A Sequential Flow Control Framework for Multi-hop Knowledge Base Question Answering","date":"2022-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/seeing-the-wood-for-the-trees-a-contrastive","slug":"seeing-the-wood-for-the-trees-a-contrastive","title":"Seeing the wood for the trees: a contrastive regularization method for the low-resource Knowledge Base Question Answering","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/arcaneqa-dynamic-program-induction-and","slug":"arcaneqa-dynamic-program-induction-and","title":"ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question Answering","date":"2022-04-17","arxiv_id":"2204.08109","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/arcaneqa-dynamic-program-induction-and#ran","syntology_url":"https://syntology.ai/paper/2204.08109","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08109"}},"official":{"repos":["dki-lab/arcaneqa"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/subgraph-retrieval-enhanced-model-for-multi","slug":"subgraph-retrieval-enhanced-model-for-multi","title":"Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering","date":"2022-02-27","arxiv_id":"2202.13296","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-base-question-answering-by-case","slug":"knowledge-base-question-answering-by-case","title":"Knowledge Base Question Answering by Case-based Reasoning over Subgraphs","date":"2022-02-22","arxiv_id":"2202.10610","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/knowledge-base-question-answering-by-case#ran","syntology_url":"https://syntology.ai/paper/2202.10610","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.10610"}},"official":{"repos":["rajarshd/cbr-subg"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/injecting-numerical-reasoning-skills-into-1","slug":"injecting-numerical-reasoning-skills-into-1","title":"Injecting Numerical Reasoning Skills into Knowledge Base Question Answering Models","date":"2021-12-12","arxiv_id":"2112.06109","repositories_listed":1,"syntology":null},{"url":"/paper/improving-embedded-knowledge-graph-multi-hop","slug":"improving-embedded-knowledge-graph-multi-hop","title":"Improving Embedded Knowledge Graph Multi-hop Question Answering by introducing Relational Chain Reasoning","date":"2021-10-25","arxiv_id":"2110.12679","repositories_listed":1,"syntology":null},{"url":"/paper/rng-kbqa-generation-augmented-iterative","slug":"rng-kbqa-generation-augmented-iterative","title":"RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering","date":"2021-09-17","arxiv_id":"2109.08678","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rng-kbqa-generation-augmented-iterative#ran","syntology_url":"https://syntology.ai/paper/2109.08678","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.08678"}},"official":{"repos":["salesforce/rng-kbqa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/formal-query-building-with-query-structure","slug":"formal-query-building-with-query-structure","title":"Formal Query Building with Query Structure Prediction for Complex Question Answering over Knowledge Base","date":"2021-09-08","arxiv_id":"2109.03614","repositories_listed":1,"syntology":null},{"url":"/paper/complex-knowledge-base-question-answering-a","slug":"complex-knowledge-base-question-answering-a","title":"Complex Knowledge Base Question Answering: A Survey","date":"2021-08-15","arxiv_id":"2108.06688","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-transitions-of-focal-entities-for","slug":"modeling-transitions-of-focal-entities-for","title":"Modeling Transitions of Focal Entities for Conversational Knowledge Base Question Answering","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/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,"repositories_listed":1,"syntology":null},{"url":"/paper/emrkbqa-a-clinical-knowledge-base-question","slug":"emrkbqa-a-clinical-knowledge-base-question","title":"emrKBQA: A Clinical Knowledge-Base Question Answering Dataset","date":"2021-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/question-answering-over-knowledge-bases-by","slug":"question-answering-over-knowledge-bases-by","title":"Leveraging Abstract Meaning Representation for Knowledge Base Question Answering","date":"2020-12-03","arxiv_id":"2012.01707","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-answer-type-prediction-task-smart-at","slug":"semantic-answer-type-prediction-task-smart-at","title":"SeMantic AnsweR Type prediction task (SMART) at ISWC 2020 Semantic Web Challenge","date":"2020-12-01","arxiv_id":"2012.00555","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-i-i-d-three-levels-of-generalization","slug":"beyond-i-i-d-three-levels-of-generalization","title":"Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases","date":"2020-11-16","arxiv_id":"2011.07743","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-complex-knowledge-base-question","slug":"few-shot-complex-knowledge-base-question","title":"Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning","date":"2020-10-29","arxiv_id":"2010.15877","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/few-shot-complex-knowledge-base-question#ran","syntology_url":"https://syntology.ai/paper/2010.15877","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.15877"}},"official":{"repos":["DevinJake/MRL-CQA"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/retrieve-program-repeat-complex-knowledge","slug":"retrieve-program-repeat-complex-knowledge","title":"Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning","date":"2020-10-29","arxiv_id":"2010.15875","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/retrieve-program-repeat-complex-knowledge#ran","syntology_url":"https://syntology.ai/paper/2010.15875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.15875"}},"official":{"repos":["DevinJake/MARL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/rubq-a-russian-dataset-for-question-answering","slug":"rubq-a-russian-dataset-for-question-answering","title":"RuBQ: A Russian Dataset for Question Answering over Wikidata","date":"2020-05-21","arxiv_id":"2005.10659","repositories_listed":1,"syntology":null},{"url":"/paper/falcon-20-an-entity-and-relation-linking","slug":"falcon-20-an-entity-and-relation-linking","title":"Falcon 2.0: An Entity and Relation Linking Tool over Wikidata","date":"2019-12-24","arxiv_id":"1912.11270","repositories_listed":1,"syntology":null},{"url":"/paper/improving-knowledge-aware-dialogue-generation","slug":"improving-knowledge-aware-dialogue-generation","title":"Improving Knowledge-aware Dialogue Generation via Knowledge Base Question Answering","date":"2019-12-16","arxiv_id":"1912.07491","repositories_listed":1,"syntology":null},{"url":"/paper/learning-representation-mapping-for-relation","slug":"learning-representation-mapping-for-relation","title":"Learning Representation Mapping for Relation Detection in Knowledge Base Question Answering","date":"2019-07-17","arxiv_id":"1907.07328","repositories_listed":1,"syntology":null},{"url":"/paper/interactive-instance-based-evaluation-of","slug":"interactive-instance-based-evaluation-of","title":"Interactive Instance-based Evaluation of Knowledge Base Question Answering","date":"2018-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-base-question-answering-via","slug":"knowledge-base-question-answering-via","title":"Knowledge Base Question Answering via Encoding of Complex Query Graphs","date":"2018-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/modeling-semantics-with-gated-graph-neural","slug":"modeling-semantics-with-gated-graph-neural","title":"Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering","date":"2018-08-13","arxiv_id":"1808.04126","repositories_listed":1,"syntology":null},{"url":"/paper/neural-machine-translation-for-query","slug":"neural-machine-translation-for-query","title":"Neural Machine Translation for Query Construction and Composition","date":"2018-06-27","arxiv_id":"1806.10478","repositories_listed":1,"syntology":null},{"url":"/paper/mixing-context-granularities-for-improved","slug":"mixing-context-granularities-for-improved","title":"Mixing Context Granularities for Improved Entity Linking on Question Answering Data across Entity Categories","date":"2018-04-23","arxiv_id":"1804.08460","repositories_listed":1,"syntology":null},{"url":"/paper/amuse-multilingual-semantic-parsing-for","slug":"amuse-multilingual-semantic-parsing-for","title":"AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data","date":"2018-02-26","arxiv_id":"1802.09296","repositories_listed":1,"syntology":null},{"url":"/paper/sparql-as-a-foreign-language","slug":"sparql-as-a-foreign-language","title":"SPARQL as a Foreign Language","date":"2017-08-25","arxiv_id":"1708.07624","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-parsing-via-staged-query-graph","slug":"semantic-parsing-via-staged-query-graph","title":"Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base","date":"2015-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"iquest-an-iterative-question-guided-framework","title":"iQUEST: An Iterative Question-Guided Framework for Knowledge Base Question Answering","date":"2025-06-02","arxiv_id":"2506.01784","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-chains-bridging-large-language-models","title":"Beyond Chains: Bridging Large Language Models and Knowledge Bases in Complex Question Answering","date":"2025-05-20","arxiv_id":"2505.14099","repositories_listed":0,"syntology":null},{"url":null,"slug":"private-lora-fine-tuning-of-open-source-llms","title":"Private LoRA Fine-tuning of Open-Source LLMs with Homomorphic Encryption","date":"2025-05-12","arxiv_id":"2505.07329","repositories_listed":0,"syntology":null},{"url":null,"slug":"mcts-kbqa-monte-carlo-tree-search-for","title":"MCTS-KBQA: Monte Carlo Tree Search for Knowledge Base Question Answering","date":"2025-02-19","arxiv_id":"2502.13428","repositories_listed":0,"syntology":null},{"url":null,"slug":"targa-targeted-synthetic-data-generation-for","title":"TARGA: Targeted Synthetic Data Generation for Practical Reasoning over Structured Data","date":"2024-12-27","arxiv_id":"2412.19544","repositories_listed":0,"syntology":null},{"url":null,"slug":"saka-an-intelligent-platform-for-semi","title":"SAKA: An Intelligent Platform for Semi-automated Knowledge Graph Construction and Application","date":"2024-10-10","arxiv_id":"2410.08094","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-learn-then-reason-model-towards","title":"A Learn-Then-Reason Model Towards Generalization in Knowledge Base Question Answering","date":"2024-06-20","arxiv_id":"2406.14763","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-few-shot-transfer-learning-for","title":"Robust Few-shot Transfer Learning for Knowledge Base Question Answering with Unanswerable Questions","date":"2024-06-20","arxiv_id":"2406.14313","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-knowledge-graph-question-answering-a","title":"Temporal Knowledge Graph Question Answering: A Survey","date":"2024-06-20","arxiv_id":"2406.14191","repositories_listed":0,"syntology":null},{"url":null,"slug":"massive-multilingual-abstract-meaning","title":"MASSIVE Multilingual Abstract Meaning Representation: A Dataset and Baselines for Hallucination Detection","date":"2024-05-29","arxiv_id":"2405.19285","repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-structured-semantics-understanding","title":"How Proficient Are Large Language Models in Formal Languages? An In-Depth Insight for Knowledge Base Question Answering","date":"2024-01-11","arxiv_id":"2401.05777","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-context-learning-for-knowledge-base","title":"In-Context Learning for Knowledge Base Question Answering for Unmanned Systems based on Large Language Models","date":"2023-11-06","arxiv_id":"2311.02956","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-nl-to-cypher-translation-for-kbqa","title":"Robust NL-to-Cypher Translation for KBQA: Harnessing Large Language Model with Chain of Prompts","date":"2023-10-28","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-in-context-schema-understanding-method-for","title":"An In-Context Schema Understanding Method for Knowledge Base Question Answering","date":"2023-10-22","arxiv_id":"2310.14174","repositories_listed":0,"syntology":null},{"url":null,"slug":"admus-a-progressive-question-answering","title":"ADMUS: A Progressive Question Answering Framework Adaptable to Multiple Knowledge Sources","date":"2023-08-09","arxiv_id":"2308.04800","repositories_listed":0,"syntology":null},{"url":null,"slug":"viskop-visual-knowledge-oriented-programming","title":"VisKoP: Visual Knowledge oriented Programming for Interactive Knowledge Base Question Answering","date":"2023-07-06","arxiv_id":"2307.03130","repositories_listed":0,"syntology":null},{"url":null,"slug":"fc-kbqa-a-fine-to-coarse-composition","title":"FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answering","date":"2023-06-26","arxiv_id":"2306.14722","repositories_listed":0,"syntology":null},{"url":null,"slug":"make-a-choice-knowledge-base-question","title":"Make a Choice! Knowledge Base Question Answering with In-Context Learning","date":"2023-05-23","arxiv_id":"2305.13972","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-parse-execute-to-parse-execute-refine","title":"From Parse-Execute to Parse-Execute-Refine: Improving Semantic Parser for Complex Question Answering over Knowledge Base","date":"2023-05-05","arxiv_id":"2305.03356","repositories_listed":0,"syntology":null},{"url":null,"slug":"pay-more-attention-to-relation-exploration","title":"Pay More Attention to Relation Exploration for Knowledge Base Question Answering","date":"2023-05-03","arxiv_id":"2305.02118","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-base-question-answering-a-semantic","title":"Knowledge Base Question Answering: A Semantic Parsing Perspective","date":"2022-09-12","arxiv_id":"2209.04994","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-enhanced-iterative-instruction","title":"Knowledge-enhanced Iterative Instruction Generation and Reasoning for Knowledge Base Question Answering","date":"2022-09-07","arxiv_id":"2209.03005","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-questions-from-wikidata-triples","title":"Generating Questions from Wikidata Triples","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-method-of-query-graph-reranking-for","title":"A Method of Query Graph Reranking for Knowledge Base Question Answering","date":"2022-04-27","arxiv_id":"2204.12808","repositories_listed":0,"syntology":null},{"url":null,"slug":"better-query-graph-selection-for-knowledge","title":"Better Query Graph Selection for Knowledge Base Question Answering","date":"2022-04-27","arxiv_id":"2204.12662","repositories_listed":0,"syntology":null},{"url":null,"slug":"cbr-ikb-a-case-based-reasoning-approach-for","title":"CBR-iKB: A Case-Based Reasoning Approach for Question Answering over Incomplete Knowledge Bases","date":"2022-04-18","arxiv_id":"2204.08554","repositories_listed":0,"syntology":null},{"url":null,"slug":"targeted-extraction-of-temporal-facts-from","title":"Targeted Extraction of Temporal Facts from Textual Resources for Improved Temporal Question Answering over Knowledge Bases","date":"2022-03-21","arxiv_id":"2203.11054","repositories_listed":0,"syntology":null},{"url":"/paper/a-two-stage-approach-towards-generalization-1","slug":"a-two-stage-approach-towards-generalization-1","title":"A Two-Stage Approach towards Generalization in Knowledge Base Question Answering","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-transpile-amr-into-sparql-1","title":"Learning to Transpile AMR into SPARQL","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/a-benchmark-for-generalizable-and","slug":"a-benchmark-for-generalizable-and","title":"A Benchmark for Generalizable and Interpretable Temporal Question Answering over Knowledge Bases","date":"2022-01-15","arxiv_id":"2201.05793","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-transpile-amr-into-sparql","title":"Learning to Transpile AMR into SPARQL","date":"2021-12-15","arxiv_id":"2112.07877","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-multi-hop-question-answering-over","title":"Few-shot Multi-hop Question Answering over Knowledge Base","date":"2021-12-14","arxiv_id":"2112.11909","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-answer-type-and-relation-prediction","title":"Semantic Answer Type and Relation Prediction Task (SMART 2021)","date":"2021-12-07","arxiv_id":"2112.07606","repositories_listed":0,"syntology":null}],"syntology_records":18,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_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'","n_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":5,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/knowledge-base-question-answering-on","since_archive":"/sota/knowledge-base-question-answering-on#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/knowledge-base-question-answering-on-grailqa","since_archive":"/sota/knowledge-base-question-answering-on-grailqa#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/knowledge-base-question-answering-on-3","since_archive":"/sota/knowledge-base-question-answering-on-3#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/knowledge-base-question-answering-on-webqsp-1","since_archive":"/sota/knowledge-base-question-answering-on-webqsp-1#since-judged","papers_judged":3,"placed":0}]},"papers_where_code_ran":16,"papers_where_code_ran_first_page":"/task/knowledge-base-question-answering/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/knowledge-base-question-answering/papers/2","json":"/task/knowledge-base-question-answering/papers/2.json","rows":36},{"order":"ran","page":1,"of":1,"url":"/task/knowledge-base-question-answering/papers/ran/1","json":"/task/knowledge-base-question-answering/papers/ran/1.json","rows":16}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"53d34d70ca5c381010812b8a1fb1cf8fba7e547404db1e7af7855cfd89617993","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}