{"id":"https://openalex.org/W7124435019","doi":"https://doi.org/10.48550/arxiv.2601.10003","title":"SocraticKG: Knowledge Graph Construction via QA-Driven Fact Extraction","display_name":"SocraticKG: Knowledge Graph Construction via QA-Driven Fact Extraction","publication_year":2026,"publication_date":"2026-01-15","ids":{"openalex":"https://openalex.org/W7124435019","doi":"https://doi.org/10.48550/arxiv.2601.10003"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.10003","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.10003","pdf_url":"https://arxiv.org/pdf/2601.10003","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.10003","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123212472","display_name":"Sanghyeok Choi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Choi, Sanghyeok","raw_affiliation_strings":["Department of Biosystems Engineering , Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biosystems Engineering , Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116144069","display_name":"Woosang Jeon","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeon, Woosang","raw_affiliation_strings":["Department of Biosystems Engineering , Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biosystems Engineering , Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081398531","display_name":"Kepeng Yang","orcid":"https://orcid.org/0000-0002-7641-9348","observed_orcids":["https://orcid.org/0000-0002-7641-9348"]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yang, Kyuseok","raw_affiliation_strings":["Department of Biosystems Engineering , Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biosystems Engineering , Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125666785","display_name":"Taehyeong Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, Taehyeong","raw_affiliation_strings":["Department of Biosystems Engineering , Seoul National University","Interdisciplinary Program in Cognitive Science , Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biosystems Engineering , Seoul National University","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Interdisciplinary Program in Cognitive Science , Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8618000149726868,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8618000149726868,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.0649000033736229,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.032499998807907104,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/knowledge-graph-construction","display_name":"knowledge graph construction","score":0.9990000128746033},{"id":"https://openalex.org/keywords/fact-extraction","display_name":"fact extraction","score":0.7590000033378601},{"id":"https://openalex.org/keywords/question-answer-pairs","display_name":"question-answer pairs","score":0.9739999771118164},{"id":"https://openalex.org/keywords/triple-extraction","display_name":"triple extraction","score":0.8360000252723694},{"id":"https://openalex.org/keywords/multi-hop-reasoning","display_name":"multi-hop reasoning","score":0.6980000138282776},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6759999990463257},{"id":"https://openalex.org/keywords/unstructured-text","display_name":"unstructured text","score":0.5899999737739563},{"id":"https://openalex.org/keywords/hotpotqa","display_name":"HotpotQA","score":0.9710000157356262}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7315000295639038},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.6309000253677368},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5282999873161316},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.5202999711036682},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.5184000134468079},{"id":"https://openalex.org/C104054115","wikidata":"https://www.wikidata.org/wiki/Q216828","display_name":"Cohesion (chemistry)","level":2,"score":0.49160000681877136},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4196999967098236},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3926999866962433},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3889000117778778},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35749998688697815},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C99436015","wikidata":"https://www.wikidata.org/wiki/Q1722436","display_name":"Relational calculus","level":4,"score":0.3411000072956085},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33709999918937683},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.32519999146461487},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.31850001215934753},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3050999939441681},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2879999876022339},{"id":"https://openalex.org/C84685590","wikidata":"https://www.wikidata.org/wiki/Q1540472","display_name":"Knowledge engineering","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.27559998631477356},{"id":"https://openalex.org/C177877439","wikidata":"https://www.wikidata.org/wiki/Q7604413","display_name":"Statistical relational learning","level":3,"score":0.2696000039577484},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.10003","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.10003","pdf_url":"https://arxiv.org/pdf/2601.10003","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2601.10003","doi":"https://doi.org/10.48550/arxiv.2601.10003","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.10003","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.10003","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.10003","pdf_url":"https://arxiv.org/pdf/2601.10003","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7124435019.pdf","grobid_xml":"https://content.openalex.org/works/W7124435019.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2624677889","https://openalex.org/W2798326384","https://openalex.org/W2808121837","https://openalex.org/W2888926795","https://openalex.org/W2948618784","https://openalex.org/W2949922292","https://openalex.org/W4321524373","https://openalex.org/W4385574107","https://openalex.org/W4389984066","https://openalex.org/W4395686609","https://openalex.org/W4407632471","https://openalex.org/W4416246560","https://openalex.org/W7131665527"],"related_works":["https://openalex.org/W4411550028","https://openalex.org/W7161013364","https://openalex.org/W7140074174","https://openalex.org/W3133833915","https://openalex.org/W4410638117","https://openalex.org/W4416548930","https://openalex.org/W6889631836","https://openalex.org/W7118635538","https://openalex.org/W3070581327","https://openalex.org/W7165898286"],"abstract_inverted_index":{"Constructing":[0],"Knowledge":[1],"Graphs":[2],"(KGs)":[3],"from":[4],"unstructured":[5],"text":[6],"provides":[7],"a":[8,22,54],"structured":[9,55],"framework":[10],"for":[11],"knowledge":[12],"representation":[13,57],"and":[14,76,105,122],"reasoning,":[15],"yet":[16],"current":[17],"LLM-based":[18],"approaches":[19],"struggle":[20],"with":[21],"fundamental":[23],"trade-off:":[24],"factual":[25,120],"coverage":[26],"often":[27],"leads":[28],"to":[29,58,64],"relational":[30,78],"fragmentation,":[31],"while":[32,125],"premature":[33],"consolidation":[34],"causes":[35],"information":[36],"loss.":[37],"To":[38],"address":[39],"this,":[40],"we":[41],"propose":[42],"SocraticKG,":[43],"an":[44],"automated":[45],"KG":[46,84],"construction":[47],"method":[48],"that":[49,94,110],"introduces":[50],"question-answer":[51],"pairs":[52],"as":[53],"intermediate":[56],"systematically":[59],"unfold":[60],"document-level":[61],"semantics":[62],"prior":[63],"triple":[65],"extraction.":[66],"By":[67],"employing":[68],"5W1H-guided":[69],"QA":[70],"expansion,":[71],"SocraticKG":[72],"captures":[73],"contextual":[74],"dependencies":[75],"implicit":[77,97],"links":[79],"typically":[80],"lost":[81],"in":[82,90],"direct":[83],"extraction":[85],"pipelines,":[86],"providing":[87],"explicit":[88],"grounding":[89],"the":[91,102,115],"source":[92],"document":[93],"helps":[95],"mitigate":[96],"reasoning":[98],"errors.":[99],"Evaluation":[100],"on":[101],"MINE":[103],"benchmark":[104],"HotpotQA":[106],"downstream":[107],"task":[108],"demonstrates":[109],"our":[111],"approach":[112],"effectively":[113],"addresses":[114],"coverage-connectivity":[116],"trade-off,":[117],"achieving":[118],"superior":[119],"retention":[121],"structural":[123],"cohesion":[124],"supporting":[126],"complex":[127],"multi-hop":[128],"reasoning.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-01-17T00:00:00"}