{"id":"https://openalex.org/W7163018176","doi":"https://doi.org/10.48550/arxiv.2605.31550","title":"Semantic Triplet Restoration: A Novel Protocol for Hierarchical Table Understanding in Large Language Models","display_name":"Semantic Triplet Restoration: A Novel Protocol for Hierarchical Table Understanding in Large Language Models","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7163018176","doi":"https://doi.org/10.48550/arxiv.2605.31550"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.31550","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31550","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,"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":null,"license_id":null,"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.2605.31550","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137527557","display_name":"Yibin Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yibin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103093395","display_name":"Fangxin Shang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shang, Fangxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123469097","display_name":"Dingrui Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Dingrui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137608273","display_name":"Yuqi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yuqi","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/T12016","display_name":"Web Data Mining and Analysis","score":0.4487000107765198,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.4487000107765198,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.06629999727010727,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.039400000125169754,"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/markup-language","display_name":"Markup language","score":0.5680999755859375},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5170999765396118},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.43970000743865967},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4180999994277954},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4090999960899353},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3921999931335449},{"id":"https://openalex.org/keywords/hierarchical-database-model","display_name":"Hierarchical database model","score":0.3799000084400177},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.3700000047683716},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.36970001459121704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8266000151634216},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.5680999755859375},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5170999765396118},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43970000743865967},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4180999994277954},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4090999960899353},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3921999931335449},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3896999955177307},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3379000127315521},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.3345000147819519},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C134752490","wikidata":"https://www.wikidata.org/wiki/Q374182","display_name":"Logical consequence","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C2776493592","wikidata":"https://www.wikidata.org/wiki/Q5158717","display_name":"Succinctness","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C202708506","wikidata":"https://www.wikidata.org/wiki/Q7449050","display_name":"Semantic compression","level":5,"score":0.3149000108242035},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.313400000333786},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C2775896111","wikidata":"https://www.wikidata.org/wiki/Q642560","display_name":"Router","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2896000146865845},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28940001130104065},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.26600000262260437}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.31550","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31550","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,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.31550","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31550","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,"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":null,"license_id":null,"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":{"Table":[0],"question":[1],"answering":[2],"requires":[3],"models":[4,41,139],"to":[5,42,101],"recover":[6],"semantic":[7,147],"relations":[8],"encoded":[9],"implicitly":[10],"by":[11],"two-dimensional":[12],"layout,":[13],"merged":[14],"cells,":[15],"and":[16,37,48,83,117,140,157],"hierarchical":[17,81],"headers.":[18],"Current":[19],"pipelines":[20],"typically":[21],"use":[22],"HTML":[23],"or":[24,106,123],"Markdown":[25],"as":[26,63],"intermediate":[27],"table":[28,142],"representations,":[29],"but":[30],"these":[31],"layout-oriented":[32],"serializations":[33],"introduce":[34],"markup":[35],"overhead":[36],"require":[38],"large":[39],"language":[40,138],"infer":[43],"header-cell":[44],"alignments":[45],"from":[46],"row":[47],"column":[49],"spans.":[50],"We":[51,90],"propose":[52],"Semantic":[53],"Triplet":[54],"Restoration":[55],"(STR),":[56],"a":[57,94],"protocol":[58],"that":[59,98,145],"rewrites":[60],"each":[61,112],"cell":[62,88],"an":[64,103],"atomic":[65],"fact":[66],",":[67],"where":[68],"the":[69,73,76,80,84,87],"item":[70],"path":[71,78],"specifies":[72,79],"row-wise":[74],"entity,":[75],"feature":[77],"attribute,":[82],"value":[85],"contains":[86],"content.":[89],"also":[91],"present":[92],"TripletQL,":[93],"lightweight":[95],"query-aware":[96],"router":[97],"uses":[99],"STR":[100,121],"select":[102],"appropriate":[104],"rendering":[105],"filtered":[107],"subset":[108],"of":[109],"triplets":[110],"for":[111,136],"question.":[113],"Across":[114],"four":[115],"Chinese":[116],"English":[118],"table-QA":[119],"benchmarks,":[120],"matches":[122],"improves":[124],"upon":[125],"HTML-based":[126],"baselines":[127],"while":[128],"reducing":[129],"input":[130],"tokens.":[131],"The":[132],"relative":[133],"benefit":[134],"grows":[135],"smaller":[137],"longer":[141],"contexts,":[143],"suggesting":[144],"explicit":[146],"representations":[148],"are":[149,159],"especially":[150],"useful":[151],"under":[152],"constrained":[153],"inference":[154],"budgets.":[155],"Code":[156],"data":[158],"available":[160],"at":[161],"https://github.com/Phoenix-ni/STR.git":[162],".":[163]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-02T00:00:00"}