{"id":"https://openalex.org/W7163687624","doi":"https://doi.org/10.48550/arxiv.2606.05564","title":"Using Large Language Models to Support High Volume Application Review for an Undergraduate Research Program","display_name":"Using Large Language Models to Support High Volume Application Review for an Undergraduate Research Program","publication_year":2026,"publication_date":"2026-06-04","ids":{"openalex":"https://openalex.org/W7163687624","doi":"https://doi.org/10.48550/arxiv.2606.05564"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.05564","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.05564","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.2606.05564","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104932479","display_name":"Varun Aggarwal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aggarwal, Varun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119373109","display_name":"Kay Kobak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kobak, Kay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5122928821","display_name":"John Howarter","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Howarter, John","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/T11986","display_name":"Scientific Computing and Data Management","score":0.14219999313354492,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.14219999313354492,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.1062999963760376,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.0658000037074089,"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/rubric","display_name":"Rubric","score":0.8824999928474426},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6391000151634216},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5070000290870667},{"id":"https://openalex.org/keywords/research-program","display_name":"Research program","score":0.3650999963283539},{"id":"https://openalex.org/keywords/program-analysis","display_name":"Program analysis","score":0.3553999960422516},{"id":"https://openalex.org/keywords/program-evaluation","display_name":"Program evaluation","score":0.35440000891685486}],"concepts":[{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.8824999928474426},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6391000151634216},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5795000195503235},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5070000290870667},{"id":"https://openalex.org/C2778035492","wikidata":"https://www.wikidata.org/wiki/Q7315176","display_name":"Research program","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C98183937","wikidata":"https://www.wikidata.org/wiki/Q2112188","display_name":"Program analysis","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C5395021","wikidata":"https://www.wikidata.org/wiki/Q1061410","display_name":"Program evaluation","level":2,"score":0.35440000891685486},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.35260000824928284},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C2778498041","wikidata":"https://www.wikidata.org/wiki/Q915466","display_name":"Academic year","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C2779041819","wikidata":"https://www.wikidata.org/wiki/Q10302238","display_name":"Undergraduate research","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C110354214","wikidata":"https://www.wikidata.org/wiki/Q6314146","display_name":"Engineering management","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C509550671","wikidata":"https://www.wikidata.org/wiki/Q126945","display_name":"Medical education","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C2777080924","wikidata":"https://www.wikidata.org/wiki/Q334667","display_name":"Storyboard","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C3019813237","wikidata":"https://www.wikidata.org/wiki/Q65089264","display_name":"Model validation","level":2,"score":0.2635999917984009}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.05564","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.05564","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.2606.05564","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.05564","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5260440707206726}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Undergraduate":[0,7],"research":[1],"programs":[2],"such":[3],"as":[4],"the":[5,41,56,67,109,136,200,209,218,234,262],"Summer":[6],"Research":[8],"Fellowship":[9],"(SURF)":[10],"at":[11,71],"Purdue":[12,72],"University":[13],"receive":[14],"thousands":[15],"of":[16,46,58,63,139,148,248],"applications":[17],"every":[18],"year,":[19],"requiring":[20],"significant":[21],"time":[22],"and":[23,33,43,82,84,125,128,214],"effort":[24,265],"for":[25,66,193,217],"program":[26,103,210,223,269],"staff":[27],"to":[28,53,107,117,168,244,261],"evaluate":[29],"each":[30,92,132,230],"submission":[31],"consistently":[32],"within":[34],"tight":[35],"timelines.":[36],"This":[37,251],"work-in-progress":[38],"paper":[39],"describes":[40],"development":[42],"initial":[44],"deployment":[45],"a":[47,86,95,246],"large":[48],"language":[49],"model":[50,110,113,179,188],"(LLM)-based":[51],"tool":[52],"assist":[54],"in":[55,144,173,187,240,256,267],"evaluation":[57],"approximately":[59,145,257],"1,200":[60,140],"student":[61],"Statements":[62],"Purpose":[64],"(SoPs)":[65],"SURF":[68,242],"2026":[69],"cycle":[70],"University.":[73],"The":[74,112,196,222],"workflow":[75],"utilizes":[76],"OpenAI":[77],"GPT":[78],"models":[79],"(GPT-4o,":[80],"GPT-5-mini,":[81],"GPT-5.2)":[83],"uses":[85],"structured":[87],"rubric":[88,174],"across":[89,178],"six":[90],"subcategories,":[91],"scored":[93,213],"on":[94],"0-3":[96],"scale.":[97],"A":[98],"few":[99],"SoPs,":[100],"graded":[101],"by":[102,204],"staff,":[104],"were":[105,176],"used":[106,239],"tune":[108],"responses.":[111],"prompt":[114],"was":[115,142,190,254],"designed":[116],"generate":[118],"both":[119],"numerical":[120],"scores,":[121],"rationales":[122],"(including":[123],"positive":[124],"negative":[126],"aspects)":[127],"short":[129],"excerpts":[130],"from":[131,166],"submission.":[133],"Using":[134],"GPT-5.2,":[135],"full":[137],"batch":[138],"SoPs":[141],"processed":[143],"4.6":[146],"hours":[147],"compute":[149],"time,":[150],"averaging":[151],"roughly":[152],"14":[153],"seconds":[154],"per":[155],"SoP":[156,162],"(with":[157],"per-SoP":[158],"timing":[159],"varying":[160],"with":[161,181,212],"length,":[163],"which":[164],"ranged":[165],"500":[167],"2,000":[169],"words).":[170],"Notable":[171],"differences":[172],"adherence":[175],"observed":[177],"versions,":[180],"GPT-5.2":[182],"adhering":[183],"most":[184],"closely.":[185],"Disagreement":[186],"scores":[189],"more":[191],"pronounced":[192],"lower-scoring":[194],"submissions.":[195],"LLM":[197],"outputs":[198,216,228],"replicated":[199],"role":[201],"previously":[202],"played":[203],"distributed":[205],"human":[206],"graders,":[207],"providing":[208],"coordinator":[211,224,252],"rationale-annotated":[215],"entire":[219],"applicant":[220],"pool.":[221],"then":[225],"reviewed":[226],"these":[227],"alongside":[229],"applicant's":[231],"SoP,":[232],"applying":[233],"same":[235],"downstream":[236],"office":[237],"criteria":[238],"prior":[241,268],"cycles,":[243],"produce":[245],"shortlist":[247],"strong":[249],"candidates.":[250],"review":[253],"completed":[255],"4":[258],"hours,":[259],"compared":[260],"multi-week":[263],"coordination":[264],"required":[266],"cycles.":[270]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-06T00:00:00"}
