{"id":"https://openalex.org/W4415250765","doi":"https://doi.org/10.1109/hpec67600.2025.11196442","title":"LLMs in Crisis Triage: Benchmarking Zero-Shot Classification of Social Media","display_name":"LLMs in Crisis Triage: Benchmarking Zero-Shot Classification of Social Media","publication_year":2025,"publication_date":"2025-09-15","ids":{"openalex":"https://openalex.org/W4415250765","doi":"https://doi.org/10.1109/hpec67600.2025.11196442"},"language":"en","primary_location":{"id":"doi:10.1109/hpec67600.2025.11196442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec67600.2025.11196442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046349306","display_name":"Emma L. McDaniel","orcid":"https://orcid.org/0000-0002-6179-5797"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Emma L. McDaniel","raw_affiliation_strings":["MIT Lincoln Laboratory,Human Resilience Technology,MA,USA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,Human Resilience Technology,MA,USA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113243791","display_name":"Samuel Scheele","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Scheele","raw_affiliation_strings":["MIT Lincoln Laboratory,Human Resilience Technology,MA,USA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,Human Resilience Technology,MA,USA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101528466","display_name":"Jeffrey Liu","orcid":"https://orcid.org/0000-0002-0784-405X"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Liu","raw_affiliation_strings":["MIT Lincoln Laboratory,Human Resilience Technology,MA,USA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory,Human Resilience Technology,MA,USA","institution_ids":["https://openalex.org/I4210122954"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046349306"],"corresponding_institution_ids":["https://openalex.org/I4210122954"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39940472,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9674999713897705,"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/T11121","display_name":"Public Relations and Crisis Communication","score":0.9143000245094299,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8015999794006348},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.7627999782562256},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.638700008392334},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.586899995803833},{"id":"https://openalex.org/keywords/triage","display_name":"Triage","score":0.4936000108718872}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8015999794006348},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.7627999782562256},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.638700008392334},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.586899995803833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5511999726295471},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4975000023841858},{"id":"https://openalex.org/C2777120189","wikidata":"https://www.wikidata.org/wiki/Q780067","display_name":"Triage","level":2,"score":0.4936000108718872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34540000557899475},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3400000035762787},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.3188999891281128},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.314300000667572},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2994000017642975},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.2759999930858612},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.2752000093460083},{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.25929999351501465},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec67600.2025.11196442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec67600.2025.11196442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Social":[0],"media":[1,40],"serves":[2],"as":[3],"a":[4,88,101],"critical":[5],"yet":[6],"challenging":[7],"data":[8],"source":[9],"during":[10],"crises,":[11],"requiring":[12],"efficient":[13],"triage":[14],"of":[15,62,85,98,103],"urgent":[16],"information.":[17],"To":[18],"address":[19],"this":[20],"need,":[21],"we":[22,51],"evaluate":[23],"22":[24],"large":[25],"language":[26],"models":[27,76,107],"on":[28],"zero-shot":[29],"classification":[30,99],"tasks-identifying":[31],"informative":[32],"posts":[33],"and":[34,55,60,67],"classifying":[35],"humanitarian":[36,104],"categoriesfrom":[37],"crisis-related":[38],"social":[39],"datasets":[41],"consolidated":[42],"in":[43,81],"CrisisBench.":[44],"Leveraging":[45],"the":[46,82,94,114],"Lincoln":[47],"Laboratory":[48],"Super":[49],"Computer,":[50],"benchmarked":[52],"both":[53],"open-access":[54,75],"commercial":[56],"models,":[57],"analyzing":[58],"performance":[59],"reliability":[61],"responses":[63],"across":[64],"languages,":[65],"datasets,":[66],"classes.":[68],"Results":[69],"reveal":[70],"distinct":[71],"model":[72],"capabilities:":[73],"smaller":[74],"like":[77],"Phi3-Medium:14b":[78],"perform":[79],"competitively":[80],"simpler":[83],"task":[84,97],"determining":[86],"whether":[87],"post":[89],"was":[90],"informative;":[91],"however":[92],"for":[93],"more":[95,109],"complicated":[96],"into":[100],"number":[102],"categories,":[105],"larger":[106],"with":[108],"parameters,":[110],"namely":[111],"GPT-4o,":[112],"performed":[113],"best.":[115]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-16T00:00:00"}