{"id":"https://openalex.org/W7162139403","doi":"https://doi.org/10.48550/arxiv.2605.21845","title":"Comparing LLM and Fine-Tuned Model Performance on NVDRS Circumstance Extraction with Varying Prompt Complexity","display_name":"Comparing LLM and Fine-Tuned Model Performance on NVDRS Circumstance Extraction with Varying Prompt Complexity","publication_year":2026,"publication_date":"2026-05-21","ids":{"openalex":"https://openalex.org/W7162139403","doi":"https://doi.org/10.48550/arxiv.2605.21845"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.21845","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21845","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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.21845","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136778097","display_name":"Geoffrey Martin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin, Geoffrey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136594871","display_name":"Xuan Zhong Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Xuan Zhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136789729","display_name":"Yifan Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Yifan","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/T12488","display_name":"Mental Health via Writing","score":0.13339999318122864,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.13339999318122864,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.10429999977350235,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T11388","display_name":"Grief, Bereavement, and Mental Health","score":0.08609999716281891,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.6707000136375427},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5688999891281128},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48590001463890076},{"id":"https://openalex.org/keywords/frontier","display_name":"Frontier","score":0.4221000075340271},{"id":"https://openalex.org/keywords/hybrid-learning","display_name":"Hybrid learning","score":0.39250001311302185},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.3450999855995178}],"concepts":[{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.6707000136375427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5701000094413757},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5688999891281128},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48590001463890076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4627000093460083},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.4221000075340271},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40540000796318054},{"id":"https://openalex.org/C3018790387","wikidata":"https://www.wikidata.org/wiki/Q869010","display_name":"Hybrid learning","level":2,"score":0.39250001311302185},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33390000462532043},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3294000029563904},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3077999949455261},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26579999923706055},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C3017944768","wikidata":"https://www.wikidata.org/wiki/Q1450463","display_name":"Poison control","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.21845","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21845","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.21845","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21845","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":"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Suicide":[0],"is":[1,107],"a":[2,39,64,134],"leading":[3],"cause":[4],"of":[5,27],"death":[6,23],"in":[7],"the":[8,13,88],"United":[9],"States,":[10],"and":[11,124],"understanding":[12],"circumstances":[14,29,86,103,143],"that":[15,43,67,97,112],"precede":[16],"it":[17],"requires":[18],"extracting":[19],"structured":[20],"information":[21],"from":[22,87],"investigation":[24],"narratives.":[25],"Many":[26],"these":[28],"require":[30],"semantic":[31],"inference":[32],"beyond":[33],"simple":[34],"keyword":[35],"matching.":[36],"We":[37,61,73,95,109],"develop":[38],"``Complexity":[40],"Score''":[41],"algorithm":[42],"analyzes":[44],"coding":[45,55],"manual":[46],"structure":[47],"to":[48],"predict":[49],"when":[50],"detailed":[51],"prompts":[52],"with":[53,119],"full":[54],"guidelines":[56],"improve":[57],"over":[58],"name-only":[59],"prompts.":[60],"then":[62],"construct":[63],"hybrid":[65,135],"approach":[66],"selects":[68],"prompt":[69],"strategy":[70],"per":[71],"circumstance.":[72],"evaluate":[74],"large":[75],"language":[76],"models":[77,146],"(LLMs)":[78],"against":[79],"fine-tuned":[80,145],"RoBERTa":[81],"on":[82,101],"25":[83],"inferentially":[84,141],"complex":[85,142],"National":[89],"Violent":[90],"Death":[91],"Reporting":[92],"System":[93],"(NVDRS).":[94],"found":[96],"LLMs":[98,138],"substantially":[99],"outperform":[100],"low-prevalence":[102],"where":[104,137],"training":[105],"data":[106],"insufficient.":[108],"further":[110],"demonstrate":[111],"our":[113],"framework":[114],"generalizes":[115],"across":[116],"frontier":[117],"LLMs,":[118],"GPT-5.2,":[120],"Gemini":[121],"2.5":[122],"Pro":[123],"Llama-3":[125],"70B":[126],"showing":[127],"consistent":[128],"performance":[129],"patterns.":[130],"These":[131],"findings":[132],"support":[133],"architecture":[136],"handle":[139,147],"rare,":[140],"while":[144],"common":[148],"ones.":[149]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-23T00:00:00"}