{"id":"https://openalex.org/W7225812103","doi":"https://doi.org/10.21203/rs.3.rs-11697563/v1","title":"What Do Resume\u2013Job Matching Benchmarks Actually Measure? Keywords, Embeddings and LLMs on Public Data","display_name":"What Do Resume\u2013Job Matching Benchmarks Actually Measure? Keywords, Embeddings and LLMs on Public Data","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225812103","doi":"https://doi.org/10.21203/rs.3.rs-11697563/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-11697563/v1","doi":"https://doi.org/10.21203/rs.3.rs-11697563/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11697563/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21203/rs.3.rs-11697563/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161453710","display_name":"Nusrat Jahan Rita","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nusrat Jahan Rita","raw_affiliation_strings":["Right Brain Solution Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Right Brain Solution Ltd","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5161453710"],"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/T13812","display_name":"AI and HR Technologies","score":0.9320999979972839,"subfield":{"id":"https://openalex.org/subfields/1407","display_name":"Organizational Behavior and Human Resource Management"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13812","display_name":"AI and HR Technologies","score":0.9320999979972839,"subfield":{"id":"https://openalex.org/subfields/1407","display_name":"Organizational Behavior and Human Resource Management"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.021400000900030136,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.014800000004470348,"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"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.775600016117096},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7491999864578247},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6660000085830688},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6414999961853027},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5504999756813049},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.53329998254776},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.48669999837875366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4652000069618225},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.34549999237060547},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34470000863075256},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29829999804496765},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.27790001034736633},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-11697563/v1","doi":"https://doi.org/10.21203/rs.3.rs-11697563/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11697563/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-11697563/v1","doi":"https://doi.org/10.21203/rs.3.rs-11697563/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11697563/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Automated":[1],"resume\u2013job":[2,23],"matching":[3],"ranks":[4],"job":[5,123,161],"candidates,":[6],"but":[7,51,64],"most":[8,79],"studies":[9],"use":[10],"private":[11],"data.":[12],"We":[13,229,243],"examine":[14],"what":[15],"is,":[16],"to":[17],"our":[18,245],"knowledge,":[19],"the":[20,62,81,122,129,133,142,160,174,179,197,205],"only":[21],"public":[22],"benchmark":[24],"with":[25,178,196,204],"graded":[26],"fit":[27,185],"labels,":[28,144,235],"comparing":[29],"keyword":[30],"methods,":[31],"sentence":[32],"embeddings":[33,48,107],"(zero-shot":[34],"and":[35,37,108,238,248],"fine-tuned)":[36],"a":[38,89,126,156,168,192,218],"small":[39],"open":[40],"LLM":[41,99],"judge":[42,100],"(Qwen3-4B).":[43],"Across":[44],"294":[45],"jobs,":[46],"zero-shot":[47,96],"perform":[49,103],"slightly":[50],"significantly":[52,104,151],"better":[53,105,152],"than":[54,106,132,153,203],"TF-IDF":[55],"(NDCG@10":[56],"0.739":[57],"vs":[58,115,186],"0.706).":[59],"Fine-tuning":[60],"improves":[61],"results,":[63],"430":[65],"of":[66,80,165,171,227],"434":[67],"test":[68],"resumes":[69],"also":[70],"appear":[71],"in":[72],"training.":[73],"In":[74,167],"cross-validation,":[75],"seeing":[76],"them":[77,93],"explains":[78],"gain":[82],"even":[83,135],"at":[84],"equal":[85],"training":[86],"size,":[87],"yet":[88],"model":[90],"trained":[91],"without":[92,213],"still":[94],"beats":[95],"methods.":[97],"The":[98],"does":[101],"not":[102],"is":[109,118],"about":[110],"850":[111],"times":[112],"slower.":[113],"Good":[114],"Potential":[116],"Fit":[117],"largely":[119],"set":[120],"by":[121,222],"and,":[124],"within":[125],"job,":[127],"follows":[128],"resume":[130],"more":[131,202],"match,":[134],"when":[136],"estimated":[137],"from":[138],"unrelated":[139],"jobs.":[140],"Against":[141],"dataset":[143,180,198],"no":[145,187],"job-aware":[146],"method":[147],"separates":[148],"these":[149],"levels":[150],"chance,":[154],"while":[155],"baseline":[157],"that":[158],"ignores":[159],"reaches":[162],"an":[163],"AUC":[164],"0.727.":[166],"blind":[169],"relabelling":[170],"150":[172],"pairs,":[173,191],"author":[175,206],"agrees":[176,195],"weakly":[177],"(\u03ba":[181,199,207],"=":[182,200,208],"0.324":[183],"for":[184],"fit);":[188],"on":[189],"40":[190],"second":[193],"annotator":[194],"0.319)":[201],"0.093).":[209],"Finally,":[210],"adding":[211],"markdown":[212,239],"changing":[214],"any":[215],"words":[216],"increases":[217],"resume's":[219],"E5":[220],"score":[221],"0.91":[223],"standard":[224],"deviations,":[225],"regardless":[226],"fit.":[228],"therefore":[230],"recommend":[231],"unseen-resume":[232],"splits,":[233],"reliable":[234],"resume-only":[236],"baselines,":[237],"removal":[240],"before":[241],"embedding.":[242],"release":[244],"code,":[246],"splits":[247],"labels.":[249]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}