{"id":"https://openalex.org/W7160037940","doi":"https://doi.org/10.48550/arxiv.2605.00245","title":"ARMOR 2025: A Military-Aligned Benchmark for Evaluating Large Language Model Safety Beyond Civilian Contexts","display_name":"ARMOR 2025: A Military-Aligned Benchmark for Evaluating Large Language Model Safety Beyond Civilian Contexts","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W7160037940","doi":"https://doi.org/10.48550/arxiv.2605.00245"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2605.00245","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.00245","pdf_url":"https://arxiv.org/pdf/2605.00245","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2605.00245","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031777439","display_name":"Sydney Johns","orcid":"https://orcid.org/0000-0002-6751-0828","observed_orcids":["https://orcid.org/0000-0002-6751-0828"]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Johns, Sydney","raw_affiliation_strings":["Virginia Polytechnic Institute and State University , Virginia , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University , Virginia , United States","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102661217","display_name":"Heng Jin","orcid":"https://orcid.org/0009-0002-4024-5574","observed_orcids":["https://orcid.org/0009-0002-4024-5574"]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jin, Heng","raw_affiliation_strings":["Virginia Polytechnic Institute and State University , Virginia , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University , Virginia , United States","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137315463","display_name":"Chaoyu Zhang","orcid":"https://orcid.org/0009-0007-8066-709X","observed_orcids":["https://orcid.org/0009-0007-8066-709X"]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Chaoyu","raw_affiliation_strings":["Virginia Polytechnic Institute and State University , Virginia , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University , Virginia , United States","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151098511","display_name":"Y. Thomas Hou","orcid":"https://orcid.org/0000-0003-3716-5768","observed_orcids":["https://orcid.org/0000-0003-3716-5768"]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hou, Y. Thomas","raw_affiliation_strings":["Virginia Polytechnic Institute and State University , Virginia , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University , Virginia , United States","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001879281","display_name":"Wenjing Lou","orcid":"https://orcid.org/0000-0002-2421-4623","observed_orcids":["https://orcid.org/0000-0002-2421-4623"]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lou, Wenjing","raw_affiliation_strings":["Virginia Polytechnic Institute and State University , Virginia , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University , Virginia , United States","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.8726000189781189,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.8726000189781189,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.03480000048875809,"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/T12888","display_name":"Military Strategy and Technology","score":0.02019999921321869,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-model-safety","display_name":"large language model safety","score":0.8809999823570251},{"id":"https://openalex.org/keywords/international-humanitarian-law","display_name":"international humanitarian law","score":0.6740000247955322},{"id":"https://openalex.org/keywords/rules-of-engagement","display_name":"rules of engagement","score":0.9940000176429749},{"id":"https://openalex.org/keywords/military-decision-making","display_name":"military decision-making","score":0.515999972820282},{"id":"https://openalex.org/keywords/refusal-behavior","display_name":"refusal behavior","score":0.45100000500679016},{"id":"https://openalex.org/keywords/multiple-choice-questions","display_name":"multiple-choice questions","score":0.640999972820282},{"id":"https://openalex.org/keywords/military-applications","display_name":"military applications","score":0.5379999876022339},{"id":"https://openalex.org/keywords/safety-alignment","display_name":"safety alignment","score":0.5080000162124634}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7056999802589417},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.474700003862381},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.4717000126838684},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.4447999894618988},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.4302000105381012},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40700000524520874},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.38350000977516174},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.3522000014781952},{"id":"https://openalex.org/C73492039","wikidata":"https://www.wikidata.org/wiki/Q377804","display_name":"Armour","level":3,"score":0.33329999446868896},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C2779072820","wikidata":"https://www.wikidata.org/wiki/Q47064","display_name":"Military personnel","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C2888476","wikidata":"https://www.wikidata.org/wiki/Q5249202","display_name":"Decision-making models","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C3017944768","wikidata":"https://www.wikidata.org/wiki/Q1450463","display_name":"Poison control","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2605.00245","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.00245","pdf_url":"https://arxiv.org/pdf/2605.00245","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2605.00245","doi":"https://doi.org/10.48550/arxiv.2605.00245","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00245","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2605.00245","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.00245","pdf_url":"https://arxiv.org/pdf/2605.00245","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, justice, and strong institutions","score":0.7297000288963318,"id":"https://metadata.un.org/sdg/16"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G2454284058","display_name":null,"funder_award_id":"N00014-24-1-2730","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5192101867","display_name":"Collaborative Research: SaTC: CORE: Medium: A Networking Perspective of Blockchain Security: Modeling, Analysis, and Defense","funder_award_id":"2154929","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7160037940.pdf","grobid_xml":"https://content.openalex.org/works/W7160037940.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7140160879","https://openalex.org/W4416372181","https://openalex.org/W4412888273","https://openalex.org/W7211919382","https://openalex.org/W7214164355","https://openalex.org/W4394867286","https://openalex.org/W7125627995","https://openalex.org/W7135026259","https://openalex.org/W7117459248","https://openalex.org/W7131133318"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,63],"(LLMs)":[3],"are":[4],"now":[5],"being":[6],"explored":[7],"for":[8,187],"defense":[9],"applications":[10],"that":[11,40,45,70,119],"require":[12],"reliable":[13],"and":[14,29,58,67,102,114,152,170],"legally":[15],"compliant":[16],"decision":[17,26,142,157],"support.":[18],"They":[19],"also":[20],"hold":[21],"significant":[22],"potential":[23],"to":[24,175],"enhance":[25],"making,":[27],"coordination,":[28],"operational":[30],"efficiency":[31],"in":[32,89,184],"military":[33,48,73,84,92,155,188],"contexts.":[34],"These":[35],"uses":[36],"demand":[37],"evaluation":[38,172],"methods":[39],"reflect":[41],"the":[42,65,94,98,103,121,136],"doctrinal":[43,109],"standards":[44],"guide":[46],"real":[47,72],"operations.":[49,74],"Existing":[50],"safety":[51,86,185],"benchmarks":[52],"focus":[53],"on":[54],"general":[55],"social":[56],"risks":[57],"do":[59],"not":[60],"test":[61],"whether":[62],"follow":[64],"legal":[66],"ethical":[68],"rules":[69],"govern":[71],"To":[75],"address":[76],"this":[77],"gap,":[78],"we":[79],"introduce":[80],"ARMOR":[81],"2025,":[82],"a":[83,132,162],"aligned":[85],"benchmark":[87,128,160],"grounded":[88,168],"three":[90],"core":[91],"doctrines":[93],"Law":[95],"of":[96,100,124,150],"War,":[97],"Rules":[99],"Engagement,":[101],"Joint":[104],"Ethics":[105],"Regulation.":[106],"We":[107],"extract":[108],"text":[110],"from":[111],"these":[112],"sources":[113],"generate":[115],"multiple":[116],"choice":[117],"questions":[118],"preserve":[120],"intended":[122],"meaning":[123],"each":[125],"rule.":[126],"The":[127],"is":[129],"organized":[130],"through":[131],"taxonomy":[133],"informed":[134],"by":[135],"Observe":[137],"Orient":[138],"Decide":[139],"Act":[140],"(OODA)":[141],"making":[143],"framework.":[144],"This":[145,159],"structure":[146],"enables":[147],"systematic":[148],"testing":[149],"accuracy":[151],"refusal":[153],"across":[154],"relevant":[156],"types.":[158],"features":[161],"structured":[163],"12-category":[164],"taxonomy,":[165],"519":[166],"doctrinally":[167],"prompts,":[169],"rigorous":[171],"procedures":[173],"applied":[174],"21":[176],"commercial":[177],"LLMs.":[178],"Evaluation":[179],"results":[180],"reveal":[181],"critical":[182],"gaps":[183],"alignment":[186],"applications.":[189]},"counts_by_year":[],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2026-05-05T00:00:00"}
