{"id":"https://openalex.org/W7139086347","doi":"https://doi.org/10.48550/arxiv.2603.16818","title":"Leveraging LLMs for Structured Information Extraction and Analysis from Cloud Incident Reports (Work In Progress Paper)","display_name":"Leveraging LLMs for Structured Information Extraction and Analysis from Cloud Incident Reports (Work In Progress Paper)","publication_year":2026,"publication_date":"2026-03-17","ids":{"openalex":"https://openalex.org/W7139086347","doi":"https://doi.org/10.48550/arxiv.2603.16818"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.16818","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16818","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.2603.16818","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081421197","display_name":"Xiaoyu Chu","orcid":"https://orcid.org/0000-0002-0353-7968"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chu, Xiaoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050418212","display_name":"Shashikant Ilager","orcid":"https://orcid.org/0000-0003-1178-6582"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ilager, Shashikant","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129889493","display_name":"Yizhen Zang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zang, Yizhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003364582","display_name":"Sacheendra Talluri","orcid":"https://orcid.org/0000-0003-3461-4919"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Talluri, Sacheendra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5121417185","display_name":"Alexandru Iosup","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iosup, Alexandru","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/T11937","display_name":"Research Data Management Practices","score":0.1598999947309494,"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"}},"topics":[{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.1598999947309494,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.10840000212192535,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.10289999842643738,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/cloud-computing","display_name":"Cloud computing","score":0.7804999947547913},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.564300000667572},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5508999824523926},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4927000105381012},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4171999990940094},{"id":"https://openalex.org/keywords/dependability","display_name":"Dependability","score":0.3978999853134155}],"concepts":[{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7804999947547913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6984000205993652},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.564300000667572},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5508999824523926},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5325999855995178},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4927000105381012},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4124999940395355},{"id":"https://openalex.org/C77019957","wikidata":"https://www.wikidata.org/wiki/Q2689057","display_name":"Dependability","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C116537","wikidata":"https://www.wikidata.org/wiki/Q2169973","display_name":"Service provider","level":3,"score":0.3528999984264374},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3179999887943268},{"id":"https://openalex.org/C32896092","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Risk management","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.275299996137619},{"id":"https://openalex.org/C134121241","wikidata":"https://www.wikidata.org/wiki/Q899301","display_name":"Yield (engineering)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27160000801086426},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.16818","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16818","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.2603.16818","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16818","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":{"Incident":[0],"management":[1],"is":[2,70],"essential":[3],"to":[4,20,29,45,61,67,83,124,196,239],"maintain":[5],"the":[6,21,24,78,162,176],"reliability":[7],"and":[8,26,40,48,108,110,119,126,139,143,148,155,190,216,227,234,241,249],"availability":[9],"of":[10,56,80,130],"cloud":[11,89,103],"computing":[12],"services.":[13],"Cloud":[14],"vendors":[15],"typically":[16],"disclose":[17],"incident":[18,90,98],"reports":[19,36,99],"public,":[22],"summarizing":[23],"failures":[25],"recovery":[27],"process":[28],"help":[30],"minimize":[31],"their":[32],"impact.":[33],"However,":[34],"such":[35],"are":[37,251],"often":[38],"lengthy":[39],"unstructured,":[41],"making":[42],"them":[43],"difficult":[44],"understand,":[46],"analyze,":[47],"use":[49,79],"for":[50,184,188,236],"long-term":[51],"dependability":[52],"improvements.":[53],"The":[54,246],"emergence":[55],"LLMs":[57,82,167,238],"offers":[58],"new":[59],"opportunities":[60],"address":[62],"this":[63,69,74],"challenge,":[64],"but":[65,199],"how":[66],"achieve":[68,168],"currently":[71],"understudied.":[72],"In":[73],"paper,":[75],"we":[76,93,117],"explore":[77],"cutting-edge":[81],"extract":[84,125,243],"key":[85,164],"information":[86],"from":[87,100],"unstructured":[88],"reports.":[91],"First,":[92],"collect":[94],"more":[95,202],"than":[96],"3,000":[97],"3":[101,137,140],"leading":[102],"service":[104],"providers":[105],"(AWS,":[106],"AZURE,":[107],"GCP),":[109],"manually":[111],"annotate":[112],"these":[113],"collected":[114],"samples.":[115],"Then,":[116],"design":[118],"compare":[120],"6":[121],"prompt":[122],"strategies":[123],"classify":[127],"different":[128],"types":[129],"information.":[131,245],"We":[132],"consider":[133],"6~LLM":[134],"models,":[135,153],"including":[136],"lightweight":[138],"state-of-the-art":[141],"(SotA),":[142],"evaluate":[144],"model":[145],"accuracy,":[146,172,214],"latency,":[147],"token":[149],"cost":[150,226],"across":[151],"datasets,":[152],"prompts,":[154],"extracted":[156],"fields.":[157],"Our":[158,229],"study":[159,230],"has":[160,191],"uncovered":[161],"following":[163],"findings:":[165],"(1)":[166],"high":[169],"metadata":[170],"extraction":[171],"$75\\%\\text{--}95\\%$":[173],"depending":[174],"on":[175],"dataset.":[177],"(2)":[178],"Few-shot":[179],"prompting":[180],"generally":[181],"improves":[182],"accuracy":[183,222],"meta-data":[185],"fields":[186],"except":[187],"classification,":[189],"better":[192],"(lower)":[193],"latency":[194],"due":[195],"shorter":[197],"output-tokens":[198],"requires":[200],"$1.5\\text{--}2\\times$":[201],"input-tokens.":[203],"(3)":[204],"Lightweight":[205],"models":[206,219],"(e.g.,":[207],"Gemini~2.0,":[208],"GPT~3.5)":[209],"offer":[210],"favorable":[211],"trade-offs":[212],"in":[213],"cost,":[215],"latency;":[217],"SotA":[218],"yield":[220],"higher":[221],"at":[223,254],"significantly":[224],"greater":[225],"latency.":[228],"provides":[231],"tools,":[232],"methodologies,":[233],"insights":[235],"leveraging":[237],"accurately":[240],"efficiently":[242],"incident-report":[244],"FAIR":[247],"data":[248],"code":[250],"publicly":[252],"available":[253],"https://github.com/atlarge-research/llm-cloud-incident-extraction.":[255]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-20T00:00:00"}