{"id":"https://openalex.org/W4406458739","doi":"https://doi.org/10.1109/bigdata62323.2024.10825505","title":"On Text Granularity and Metric Frameworks for Large Language Model Content Detection","display_name":"On Text Granularity and Metric Frameworks for Large Language Model Content Detection","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406458739","doi":"https://doi.org/10.1109/bigdata62323.2024.10825505"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825505","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825505","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5103189799","display_name":"Linh Le","orcid":"https://orcid.org/0000-0002-0087-3448"},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Linh Le","raw_affiliation_strings":["Kennesaw State University,College of Computing and Software Engineering,Kennesaw,Georgia,USA"],"affiliations":[{"raw_affiliation_string":"Kennesaw State University,College of Computing and Software Engineering,Kennesaw,Georgia,USA","institution_ids":["https://openalex.org/I172980758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022399611","display_name":"Dung Thuy Tran","orcid":"https://orcid.org/0009-0006-7304-1358"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I1283280774","display_name":"Brigham and Women's Hospital","ror":"https://ror.org/04b6nzv94","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283280774","https://openalex.org/I48633490"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dung Tran","raw_affiliation_strings":["Harvard Medical School,Brigham and Women’s Hospital,Boston,Massachusetts,USA"],"affiliations":[{"raw_affiliation_string":"Harvard Medical School,Brigham and Women’s Hospital,Boston,Massachusetts,USA","institution_ids":["https://openalex.org/I1283280774","https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103189799"],"corresponding_institution_ids":["https://openalex.org/I172980758"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23705004,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8301","last_page":"8308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.785673975944519},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.7728085517883301},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.74152672290802},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.536381185054779},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42370742559432983},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37180307507514954},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20399853587150574},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08582413196563721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.785673975944519},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.7728085517883301},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.74152672290802},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.536381185054779},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42370742559432983},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37180307507514954},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20399853587150574},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08582413196563721},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825505","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825505","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1810943226","https://openalex.org/W2011301426","https://openalex.org/W2096733369","https://openalex.org/W2130942839","https://openalex.org/W2156740722","https://openalex.org/W2171590421","https://openalex.org/W2912924812","https://openalex.org/W2938704169","https://openalex.org/W2963096510","https://openalex.org/W2963123047","https://openalex.org/W2963620441","https://openalex.org/W2963748441","https://openalex.org/W2965373594","https://openalex.org/W2968297680","https://openalex.org/W2969958763","https://openalex.org/W2970641574","https://openalex.org/W3016473712","https://openalex.org/W3034287667","https://openalex.org/W3035965352","https://openalex.org/W3046357466","https://openalex.org/W3099878876","https://openalex.org/W3100715140","https://openalex.org/W3150635270","https://openalex.org/W4205185581","https://openalex.org/W4224308101","https://openalex.org/W4288089799","https://openalex.org/W4288334893","https://openalex.org/W4292779060","https://openalex.org/W4306178233","https://openalex.org/W4318149317","https://openalex.org/W4318351452","https://openalex.org/W4322718191","https://openalex.org/W4362515116","https://openalex.org/W4377864459","https://openalex.org/W4378770589","https://openalex.org/W4383199672","https://openalex.org/W4385149039","https://openalex.org/W4385245566","https://openalex.org/W4385565281","https://openalex.org/W4391212792","https://openalex.org/W6638273328","https://openalex.org/W6679436768","https://openalex.org/W6715605506","https://openalex.org/W6761551260","https://openalex.org/W6764055196","https://openalex.org/W6766673545","https://openalex.org/W6767057552","https://openalex.org/W6767101625","https://openalex.org/W6769627184","https://openalex.org/W6776148200","https://openalex.org/W6776403474","https://openalex.org/W6778883912","https://openalex.org/W6810081322","https://openalex.org/W6846361487","https://openalex.org/W6848670183","https://openalex.org/W6848955896","https://openalex.org/W6850625674","https://openalex.org/W6851775633","https://openalex.org/W6852555712","https://openalex.org/W6852662235","https://openalex.org/W6861750401"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2059697060","https://openalex.org/W936373746","https://openalex.org/W2975817033","https://openalex.org/W4256502920","https://openalex.org/W4382701072"],"abstract_inverted_index":{"Breakthroughs":[0],"in":[1,48,58,142,205],"Large":[2],"Language":[3],"Models":[4],"(LLMs)":[5],"have":[6],"allowed":[7],"Artificial":[8],"Intelligence":[9],"(AI)":[10],"assistant":[11],"systems":[12],"to":[13,45,77,113,121,190,210,219],"provide":[14],"quality":[15],"information":[16,53],"with":[17],"conveniences.":[18],"An":[19],"issue":[20],"is":[21,34,98,132],"paralleling":[22],"the":[23,28,68,81,84,106,115,130,150,155,158,223],"advantages,":[24],"however.":[25],"One":[26],"among":[27],"problems":[29],"of":[30,41,146,184,222],"LLM":[31,59,94],"generated":[32],"content":[33,60],"that":[35,40,97],"they":[36],"seem":[37],"indistinguishable":[38],"from":[39,125,133,149,172],"human":[42,134,173],"which":[43,72],"leads":[44],"numerous":[46],"issues":[47],"areas":[49],"like":[50],"science,":[51],"education,":[52],"security,":[54],"etc.":[55],"Furthermore,":[56],"approaches":[57],"detection":[61,96,107],"are":[62,180],"either":[63,154],"computationally":[64],"expensive":[65],"or":[66,135,144,157,177],"need":[67],"LLMs\u2019":[69],"internal":[70],"computations":[71],"make":[73],"them":[74],"more":[75],"difficult":[76],"be":[78,140],"used":[79],"by":[80],"public.":[82],"Addressing":[83],"research":[85],"gap,":[86],"we":[87],"present":[88],"a":[89,118],"metric":[90,111],"learning":[91,112],"framework":[92,108,138,199],"for":[93,100],"text":[95,120,147],"balanced":[99],"resources,":[101],"accessibility,":[102],"and":[103,127,170,174,207,214],"performance.":[104],"Specifically,":[105],"relies":[109],"on":[110],"evaluate":[114],"similarity":[116],"between":[117],"given":[119],"an":[122],"equivalent":[123],"example":[124],"LLMs":[126],"verify":[128],"whether":[129],"former":[131],"AI.":[136],"The":[137],"can":[139],"trained":[141],"triplets":[143],"pairs":[145],"instances":[148],"same":[151],"contexts":[152,169],"at":[153],"full-text":[156],"sentence":[159],"granularity":[160],"levels.":[161],"For":[162],"benchmarking,":[163],"five":[164],"corpora":[165],"totalling":[166],"over":[167],"95,000":[168],"responses":[171],"GPT-3.5":[175],"TURBO":[176,179],"GPT-4":[178],"developed.":[181],"In":[182],"term":[183],"performance,":[185],"our":[186],"architectures":[187],"maintain":[188],"0.87":[189],"0.95":[191],"F1":[192],"scores":[193],"throughout":[194],"multiple":[195],"experiment":[196],"settings.":[197],"Our":[198],"also":[200],"requires":[201],"much":[202],"less":[203],"time":[204],"training":[206],"inference":[208],"compared":[209],"RoBERTa,":[211],"LLaMA":[212],"3,":[213],"Ghostbuster,":[215],"while":[216],"having":[217],"90%":[218],"150%":[220],"performances":[221],"best":[224],"benchmark.":[225]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}