{"id":"https://openalex.org/W7162019031","doi":"https://doi.org/10.48550/arxiv.2605.20254","title":"Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting","display_name":"Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting","publication_year":2026,"publication_date":"2026-05-18","ids":{"openalex":"https://openalex.org/W7162019031","doi":"https://doi.org/10.48550/arxiv.2605.20254"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.20254","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20254","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.20254","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136666905","display_name":"Amritansh Maurya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maurya, Amritansh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136667562","display_name":"Navjot Singh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Singh, Navjot","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136679003","display_name":"Mohammed Javed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Javed, Mohammed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053010867","display_name":"Omar Moured","orcid":"https://orcid.org/0000-0003-4227-8417"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moured, Omar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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/T10028","display_name":"Topic Modeling","score":0.34790000319480896,"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":0.34790000319480896,"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":0.09459999948740005,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.07970000058412552,"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/table","display_name":"Table (database)","score":0.705299973487854},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6721000075340271},{"id":"https://openalex.org/keywords/row","display_name":"Row","score":0.6134999990463257},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.45829999446868896},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.43720000982284546},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4343999922275543},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4133000075817108}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7279999852180481},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.705299973487854},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6721000075340271},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.6134999990463257},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.45829999446868896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45329999923706055},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.43720000982284546},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4343999922275543},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40619999170303345},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.39809998869895935},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3000999987125397},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29649999737739563},{"id":"https://openalex.org/C104140500","wikidata":"https://www.wikidata.org/wiki/Q2088159","display_name":"Row and column spaces","level":3,"score":0.2924000024795532},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29010000824928284},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.20254","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20254","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.20254","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20254","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.4017212390899658}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"shown":[5],"promising":[6],"results":[7],"on":[8,14,43,120,137],"NLP":[9],"tasks,":[10],"however,":[11],"their":[12],"performance":[13,142,165],"tabular":[15,45],"data":[16],"still":[17],"needs":[18],"research":[19],"attention,":[20],"because":[21],"Table":[22],"Question-Answering":[23],"(TQA)":[24],"requires":[25],"precise":[26],"cell":[27],"retrieval":[28],"and":[29,58,82,91,94,122,136,145,151,176],"multi-step":[30],"structured":[31,72],"reasoning.":[32],"Existing":[33],"work":[34],"improves":[35,128],"TQA":[36,68],"either":[37],"by":[38,133],"fine-tuning":[39],"or":[40],"training":[41],"LLMs":[42,116],"task-specific":[44],"data,":[46],"but":[47],"often":[48],"lacks":[49],"verifiable":[50],"control":[51],"over":[52,129,143],"how":[53],"the":[54,111,130,164],"model":[55],"navigates":[56,80],"tables":[57],"derives":[59],"answers.":[60],"In":[61],"this":[62],"work,":[63],"we":[64],"propose":[65],"a":[66,85],"training-free":[67],"approach":[69],"with":[70],"two":[71],"prompting":[73],"frameworks:":[74],"TableGrid":[75],"Navigation":[76],"(TGN),":[77],"which":[78,99],"iteratively":[79],"rows":[81],"columns":[83,101],"via":[84],"three-module":[86],"loop":[87],"to":[88,110,159,167],"locate":[89],"evidence":[90],"refine":[92],"answers,":[93],"Progressive":[95],"Inference":[96],"Prompting":[97],"(PIP),":[98],"enforces":[100],"identification":[102],"for":[103,179],"explicit":[104],"progressive":[105],"row":[106],"selection":[107],"constraint":[108],"according":[109],"query.":[112],"We":[113],"evaluate":[114],"17":[115],"against":[117],"6":[118],"baselines":[119],"TableBench":[121],"FeTaQa":[123],"dataset.":[124],"On":[125],"TableBench,":[126],"TGN":[127,152],"strongest":[131],"baseline":[132],"3.8":[134],"points,":[135],"FeTaQa,":[138],"PIP":[139,150],"achieves":[140],"SOTA":[141],"ReAct":[144],"Chain-of-Thought.":[146],"Beyond":[147],"inference-time":[148],"gains,":[149],"can":[153],"also":[154],"serve":[155],"as":[156],"supervision":[157],"templates":[158],"fine-tune":[160],"small":[161],"models,":[162],"narrowing":[163],"gap":[166],"much":[168],"larger":[169],"architectures":[170],"in":[171],"resource-constrained":[172],"settings,":[173],"offering":[174],"versatile":[175],"cost-efficient":[177],"solution":[178],"TQA.":[180]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-22T00:00:00"}