{"id":"https://openalex.org/W4415344867","doi":"https://doi.org/10.48550/arxiv.2507.03674","title":"STRUCTSENSE: A Task-Agnostic Agentic Framework for Structured Information Extraction with Human-In-The-Loop Evaluation and Benchmarking","display_name":"STRUCTSENSE: A Task-Agnostic Agentic Framework for Structured Information Extraction with Human-In-The-Loop Evaluation and Benchmarking","publication_year":2025,"publication_date":"2025-07-04","ids":{"openalex":"https://openalex.org/W4415344867","doi":"https://doi.org/10.48550/arxiv.2507.03674"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2507.03674","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2507.03674","pdf_url":"https://arxiv.org/pdf/2507.03674","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/2507.03674","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069339163","display_name":"Tek Raj Chhetri","orcid":"https://orcid.org/0000-0002-3905-7878","observed_orcids":["https://orcid.org/0000-0002-3905-7878"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chhetri, Tek Raj","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006957814","display_name":"Yibei Chen","orcid":"https://orcid.org/0000-0003-2882-0900","observed_orcids":["https://orcid.org/0000-0003-2882-0900"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yibei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Trivedi, Puja","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Trivedi, Puja","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031653755","display_name":"Dorota Jarecka","orcid":"https://orcid.org/0000-0001-8282-2988","observed_orcids":["https://orcid.org/0000-0001-8282-2988"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jarecka, Dorota","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120061242","display_name":"Saif Haobsh","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haobsh, Saif","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075752483","display_name":"Patrick L. Ray","orcid":"https://orcid.org/0000-0002-5260-9315","observed_orcids":["https://orcid.org/0000-0002-5260-9315"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ray, Patrick","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074982934","display_name":"Lydia Ng","orcid":"https://orcid.org/0000-0002-7499-3514","observed_orcids":["https://orcid.org/0000-0002-7499-3514"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ng, Lydia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051194003","display_name":"Satrajit Ghosh","orcid":"https://orcid.org/0000-0002-5312-6729","observed_orcids":["https://orcid.org/0000-0002-5312-6729","https://orcid.org/0000-0001-7657-2214","https://orcid.org/0000-0003-0950-9260"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ghosh, Satrajit S.","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":true,"cited_by_count":10,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9740999937057495,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9740999937057495,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.015399999916553497,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.004100000020116568,"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/structured-information-extraction","display_name":"structured data extraction","score":0.9800000190734863},{"id":"https://openalex.org/keywords/scientific-publications","display_name":"scientific publications","score":0.6549999713897705},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.871999979019165},{"id":"https://openalex.org/keywords/agentic-framework","display_name":"agentic framework","score":0.6039999723434448},{"id":"https://openalex.org/keywords/human-in-the-loop-evaluation","display_name":"human-in-the-loop evaluation","score":0.9200000166893005},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.753000020980835},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"named entity recognition","score":0.925000011920929},{"id":"https://openalex.org/keywords/neuroscience-literature","display_name":"neuroscience literature","score":0.7160000205039978},{"id":"https://openalex.org/keywords/metadata-extraction","display_name":"metadata extraction","score":0.6230000257492065},{"id":"https://openalex.org/keywords/assessment-tools","display_name":"assessment instruments","score":0.7289999723434448},{"id":"https://openalex.org/keywords/concept-mapping","display_name":"concept mapping","score":0.6069999933242798},{"id":"https://openalex.org/keywords/task-generalization","display_name":"task generalization","score":0.6809999942779541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7817000150680542},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7297999858856201},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6315000057220459},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.551800012588501},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5303000211715698},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5098999738693237},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.40119999647140503},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.392300009727478},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.38429999351501465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37720000743865967},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.3734999895095825},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33320000767707825},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30570000410079956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3019999861717224},{"id":"https://openalex.org/C45983554","wikidata":"https://www.wikidata.org/wiki/Q3412851","display_name":"Information quality","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C87868495","wikidata":"https://www.wikidata.org/wiki/Q750843","display_name":"Information processing","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.2750000059604645},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C186886427","wikidata":"https://www.wikidata.org/wiki/Q5441213","display_name":"Feedback loop","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2583000063896179},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C186625053","wikidata":"https://www.wikidata.org/wiki/Q1130191","display_name":"Information overload","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2507.03674","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2507.03674","pdf_url":"https://arxiv.org/pdf/2507.03674","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.2507.03674","doi":"https://doi.org/10.48550/arxiv.2507.03674","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.03674","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:2507.03674","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2507.03674","pdf_url":"https://arxiv.org/pdf/2507.03674","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":[{"id":"https://openalex.org/G9000877478","display_name":"ReproNim: A Center for Reproducible Neuroimaging Computation","funder_award_id":"P41EB019936","funder_id":"https://openalex.org/F4320337363","funder_display_name":"National Institute of Biomedical Imaging and Bioengineering"},{"id":"https://openalex.org/G9000889133","display_name":"DANDI: Distributed Archives for Neurophysiology Data Integration","funder_award_id":"R24MH117295","funder_id":"https://openalex.org/F4320337346","funder_display_name":"National Institute of Mental Health"},{"id":"https://openalex.org/G9000902837","display_name":"An extensible brain knowledge base and toolset spanning modalities for multi-species data-driven cell types","funder_award_id":"U24MH130918","funder_id":"https://openalex.org/F4320337346","funder_display_name":"National Institute of Mental Health"},{"id":"https://openalex.org/G933292660","display_name":"BBQS AI Resource and Data Coordinating Center (BARD.CC)","funder_award_id":"1u24mh136628-01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320310260","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337346","display_name":"National Institute of Mental Health","ror":"https://ror.org/04xeg9z08"},{"id":"https://openalex.org/F4320337363","display_name":"National Institute of Biomedical Imaging and Bioengineering","ror":"https://ror.org/00372qc85"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415344867.pdf","grobid_xml":"https://content.openalex.org/works/W4415344867.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2071879021","https://openalex.org/W3202771869","https://openalex.org/W4389523710","https://openalex.org/W4391836235","https://openalex.org/W4400433884","https://openalex.org/W4404239715","https://openalex.org/W4404534210","https://openalex.org/W4410313004","https://openalex.org/W4410637017","https://openalex.org/W4412945537","https://openalex.org/W4416036549","https://openalex.org/W4416043407"],"related_works":["https://openalex.org/W7126091349","https://openalex.org/W4311409687","https://openalex.org/W4391836235","https://openalex.org/W7127377800","https://openalex.org/W7214025583","https://openalex.org/W7135201085","https://openalex.org/W7164405041","https://openalex.org/W7160851656","https://openalex.org/W7203923425","https://openalex.org/W7126444615"],"abstract_inverted_index":{"Extracting":[0],"structured":[1],"information":[2],"from":[3,74,84],"scientific":[4,75],"literature":[5,86],"is":[6],"critical":[7],"for":[8,49],"accelerating":[9],"discovery,":[10],"yet":[11],"Large":[12],"Language":[13],"Models":[14],"(LLMs)":[15],"often":[16],"struggle":[17],"in":[18],"specialized":[19],"domains":[20,142],"that":[21,38,144],"require":[22],"expert":[23],"knowledge":[24],"and":[25,46,71,79,100,109,133,153],"generalize":[26],"poorly":[27],"across":[28,90,140,147],"tasks.":[29],"We":[30,53],"introduce":[31],"\\textsc{StructSense},":[32],"a":[33],"modular,":[34],"task-agnostic,":[35],"open-source":[36],"framework":[37],"integrates":[39],"ontology-guided":[40],"symbolic":[41],"knowledge,":[42],"agentic":[43],"self-evaluative":[44],"refinement,":[45],"human-in-the-loop":[47],"validation":[48],"robust":[50],"domain-aware":[51],"extraction.":[52],"evaluate":[54],"\\textsc{StructSense}":[55,145],"on":[56],"three":[57,141],"tasks":[58,148],"of":[59,65,128],"increasing":[60],"semantic":[61,136],"complexity:":[62],"schema-based":[63],"extraction":[64,73],"assessment":[66],"instruments":[67],"(91--100\\%":[68],"accuracy),":[69],"metadata":[70],"resource":[72],"papers":[76],"(86--93\\%":[77],"overall),":[78],"named":[80],"entity":[81],"recognition":[82],"(NER)":[83],"neuroscience":[85],"(58--75\\%":[87],"label":[88],"accuracy":[89],"8,882":[91],"entities).":[92],"On":[93],"two":[94],"biomedical":[95],"NER":[96],"benchmarks":[97],"(NCBI":[98],"Disease":[99],"S800":[101],"Species),":[102],"the":[103],"system":[104],"achieves":[105,126],"$\\geq$90\\%":[106],"relaxed":[107],"recall":[108,112],"62.5--85.8\\%":[110],"strict":[111,131],"while":[113,149],"extracting":[114],"1,000--3,600":[115],"additional":[116],"entities":[117],"beyond":[118],"gold":[119],"annotations.":[120],"The":[121],"local":[122],"concept":[123],"mapping":[124],"service":[125],"Hits@1":[127],"62--82\\%":[129],"under":[130,135],"matching":[132],"68--86\\%":[134],"matching.":[137],"These":[138],"results":[139],"demonstrate":[143],"generalizes":[146],"maintaining":[150],"source":[151],"grounding":[152],"provenance":[154],"transparency.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-20T00:00:00"}