{"id":"https://openalex.org/W4416203835","doi":"https://doi.org/10.1145/3712285.3759803","title":"Demystifying the Resilience of Large Language Model Inference: An End-to-End Perspective","display_name":"Demystifying the Resilience of Large Language Model Inference: An End-to-End Perspective","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4416203835","doi":"https://doi.org/10.1145/3712285.3759803"},"language":null,"primary_location":{"id":"doi:10.1145/3712285.3759803","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759803","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3712285.3759803","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102015308","display_name":"Yu Sun","orcid":"https://orcid.org/0000-0001-7740-6082"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yu Sun","raw_affiliation_strings":["George Mason University (GMU), Fairfax, USA"],"affiliations":[{"raw_affiliation_string":"George Mason University (GMU), Fairfax, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120649212","display_name":"Zachary Coalson","orcid":"https://orcid.org/0009-0006-0821-3432"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zachary Coalson","raw_affiliation_strings":["Oregon State University, Corvallis, USA"],"affiliations":[{"raw_affiliation_string":"Oregon State University, Corvallis, USA","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016169662","display_name":"Shiyang Chen","orcid":"https://orcid.org/0000-0003-2626-7865"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiyang Chen","raw_affiliation_strings":["Rutgers University, New Brunswick, Piscataway, USA"],"affiliations":[{"raw_affiliation_string":"Rutgers University, New Brunswick, Piscataway, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100623301","display_name":"Hang Liu","orcid":"https://orcid.org/0000-0001-6323-7388"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hang Liu","raw_affiliation_strings":["Rutgers University, New Brunswick, Piscataway, USA"],"affiliations":[{"raw_affiliation_string":"Rutgers University, New Brunswick, Piscataway, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422982","display_name":"Zhao Zhang","orcid":"https://orcid.org/0000-0001-5921-0035"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhao Zhang","raw_affiliation_strings":["Rutgers University, New Brunswick, Piscataway, USA"],"affiliations":[{"raw_affiliation_string":"Rutgers University, New Brunswick, Piscataway, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102751625","display_name":"Sanghyun Hong","orcid":"https://orcid.org/0000-0003-4154-7611"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanghyun Hong","raw_affiliation_strings":["Oregon State University, Corvallis, USA"],"affiliations":[{"raw_affiliation_string":"Oregon State University, Corvallis, USA","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bo Fang","orcid":"https://orcid.org/0000-0001-9721-3982"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Fang","raw_affiliation_strings":["Pacific Northwest National Laboratory (PNNL), Richland, USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory (PNNL), Richland, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101518966","display_name":"Lishan Yang","orcid":"https://orcid.org/0000-0002-0735-8617"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lishan Yang","raw_affiliation_strings":["George Mason University (GMU), Fairfax, USA"],"affiliations":[{"raw_affiliation_string":"George Mason University (GMU), Fairfax, USA","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5102015308"],"corresponding_institution_ids":["https://openalex.org/I162714631"],"apc_list":null,"apc_paid":null,"fwci":4.7137,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95334428,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1127","last_page":"1144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2554999887943268,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2554999887943268,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.08789999783039093,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0828000009059906,"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/perspective","display_name":"Perspective (graphical)","score":0.6669999957084656},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.6003999710083008},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5228000283241272},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.47360000014305115},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.4523000121116638},{"id":"https://openalex.org/keywords/psychological-resilience","display_name":"Psychological resilience","score":0.3903999924659729},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.34630000591278076},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.3122999966144562}],"concepts":[{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6669999957084656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6029999852180481},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.6003999710083008},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5228000283241272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.510200023651123},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.47360000014305115},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.4523000121116638},{"id":"https://openalex.org/C137176749","wikidata":"https://www.wikidata.org/wiki/Q4105337","display_name":"Psychological resilience","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3781999945640564},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.298799991607666},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C11693617","wikidata":"https://www.wikidata.org/wiki/Q181839","display_name":"Pragmatics","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3712285.3759803","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759803","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3712285.3759803","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759803","pdf_url":null,"source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2315690200","display_name":null,"funder_award_id":"66150, DE-AC05-76RL01830.","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4715692124","display_name":null,"funder_award_id":"2402940, 2410856, 2417750, 2018631","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1965936844","https://openalex.org/W1966243865","https://openalex.org/W2021337678","https://openalex.org/W2027716782","https://openalex.org/W2143137068","https://openalex.org/W2150884987","https://openalex.org/W2318507312","https://openalex.org/W2327355331","https://openalex.org/W2587741066","https://openalex.org/W2626058548","https://openalex.org/W2758950307","https://openalex.org/W2767260595","https://openalex.org/W2767966988","https://openalex.org/W2770542984","https://openalex.org/W2809188712","https://openalex.org/W2883506058","https://openalex.org/W2884175902","https://openalex.org/W2901073342","https://openalex.org/W2927956055","https://openalex.org/W2933569951","https://openalex.org/W2946609015","https://openalex.org/W2963323070","https://openalex.org/W2963327228","https://openalex.org/W2982138961","https://openalex.org/W3002446690","https://openalex.org/W3012032150","https://openalex.org/W3046764219","https://openalex.org/W3101271453","https://openalex.org/W3173360659","https://openalex.org/W3187862527","https://openalex.org/W3194676777","https://openalex.org/W3197312262","https://openalex.org/W4253391807","https://openalex.org/W4384026312","https://openalex.org/W4388212323","https://openalex.org/W4388662069","https://openalex.org/W4391801271","https://openalex.org/W4395106422","https://openalex.org/W4399282312","https://openalex.org/W4404133402","https://openalex.org/W4408029605","https://openalex.org/W4409372178","https://openalex.org/W4414210324"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"are":[3,67],"known":[4],"to":[5,8,29,71,119],"be":[6],"resilient":[7,70],"random":[9,52,72],"bitwise":[10,53],"faults":[11,54],"in":[12,55,93],"their":[13],"parameters.":[14],"However,":[15],"this":[16,31,40],"resilience":[17,117],"has":[18],"primarily":[19],"been":[20],"established":[21],"through":[22],"studies":[23],"of":[24,51,86,130],"classification":[25],"models.":[26],"The":[27],"extent":[28],"which":[30],"claim":[32],"holds":[33],"for":[34],"large-language":[35],"models":[36,66,120],"remains":[37],"under-explored.":[38],"In":[39],"work,":[41],"we":[42,114],"conduct":[43],"an":[44,83],"extensive":[45],"measurement":[46],"study":[47],"on":[48],"the":[49,87],"impact":[50],"commercial-scale":[56],"language":[57,65],"model":[58],"inference.":[59],"We":[60],"first":[61],"expose":[62],"that":[63,100],"these":[64],"not":[68],"truly":[69],"bit-flips.":[73],"While":[74],"aggregate":[75],"metrics":[76],"such":[77,125],"as":[78,126],"accuracy":[79],"may":[80],"suggest":[81],"resilience,":[82],"in-depth":[84],"inspection":[85],"generated":[88],"outputs":[89],"shows":[90,99],"significant":[91],"degradation":[92],"text":[94],"quality.":[95],"Our":[96],"analysis":[97,118],"also":[98],"tasks":[101],"requiring":[102],"more":[103,107],"complex":[104],"reasoning":[105,123],"suffer":[106],"from":[108],"performance":[109],"and":[110],"quality":[111],"degradation.":[112],"Moreover,":[113],"extend":[115],"our":[116],"with":[121],"augmented":[122],"capabilities,":[124],"Chain-of-Thought":[127],"or":[128],"Mixture":[129],"Experts":[131],"architectures.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-12T00:00:00"}