{"id":"https://openalex.org/W7160913874","doi":"https://doi.org/10.48550/arxiv.2605.10791","title":"PathISE: Learning Informative Path Supervision for Knowledge Graph Question Answering","display_name":"PathISE: Learning Informative Path Supervision for Knowledge Graph Question Answering","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160913874","doi":"https://doi.org/10.48550/arxiv.2605.10791"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.10791","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10791","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.10791","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135971739","display_name":"Shengxiang Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Shengxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135989381","display_name":"Chao Lei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei, Chao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135978539","display_name":"Jey Han Lau","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lau, Jey Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135956034","display_name":"Jianzhong Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi, Jianzhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.8424999713897705,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.8424999713897705,"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/T10028","display_name":"Topic Modeling","score":0.09809999912977219,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.02979999966919422,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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","display_name":"Knowledge graph","score":0.7222999930381775},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6434999704360962},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6032000184059143},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.48100000619888306},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.43230000138282776},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4075999855995178},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.337799996137619},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.31630000472068787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7609999775886536},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.7222999930381775},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6434999704360962},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6032000184059143},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.48100000619888306},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.43230000138282776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.427700012922287},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35839998722076416},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33079999685287476},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2946000099182129},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C2776291881","wikidata":"https://www.wikidata.org/wiki/Q6423378","display_name":"Knowledge level","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2856000065803528},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2563000023365021},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.10791","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10791","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.10791","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10791","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Knowledge":[0,13],"Graph":[1],"Question":[2],"Answering":[3],"(KGQA)":[4],"aims":[5],"to":[6,25,39,62,91,114],"answer":[7,120],"user":[8],"questions":[9],"by":[10],"reasoning":[11],"over":[12],"Graphs":[14],"(KGs).":[15],"Recent":[16],"KGQA":[17,126,135,146],"methods":[18],"mainly":[19],"follow":[20],"the":[21,86,112],"retrieval-augmented":[22],"generation":[23],"paradigm":[24],"ground":[26],"Large":[27],"Language":[28],"Models~(LLMs)":[29],"with":[30],"structured":[31],"knowledge":[32],"from":[33,43,75],"KGs.":[34],"However,":[35],"training":[36],"effective":[37],"models":[38],"retrieve":[40],"question-relevant":[41,53],"evidence":[42,117],"KGs":[44],"typically":[45],"requires":[46],"high-quality":[47,72],"intermediate":[48,73],"supervision":[49,74,97,140,153],"signals,":[50],"such":[51],"as":[52],"paths":[54,90,108],"or":[55,133],"subgraphs,":[56],"which":[57],"are":[58,109],"time-":[59],"and":[60,137],"resource-intensive":[61],"obtain.":[63],"We":[64],"propose":[65],"PathISE,":[66],"a":[67,80],"novel":[68],"framework":[69],"for":[70,118],"learning":[71],"answer-level":[76],"labels.":[77],"PathISE":[78,130],"introduces":[79],"lightweight":[81],"transformer-based":[82],"estimator":[83],"that":[84,129,142],"estimates":[85],"informativeness":[87],"of":[88],"relation":[89],"construct":[92],"pseudo":[93],"path-level":[94],"supervision.":[95],"This":[96],"is":[98,158],"then":[99],"distilled":[100],"into":[101],"an":[102],"LLM":[103],"path":[104],"generator,":[105],"whose":[106],"generated":[107],"grounded":[110],"in":[111],"KG":[113],"provide":[115],"compact":[116],"inductive":[119],"reasoning.":[121],"ExtensiveISE":[122],"experiments":[123],"on":[124,150],"three":[125],"benchmarks":[127],"show":[128],"achieves":[131],"competitive":[132],"state-of-the-art":[134],"performance,":[136],"provides":[138],"reusable":[139],"signals":[141],"can":[143],"enhance":[144],"existing":[145],"models,":[147],"without":[148],"relying":[149],"costly":[151],"LLM-refined":[152],"signals.":[154],"Our":[155],"source":[156],"code":[157],"available":[159],"at":[160],"https://anonymous.4open.science/r/PathISE-2F87.":[161]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-13T00:00:00"}