{"id":"https://openalex.org/W7152746343","doi":"https://doi.org/10.1145/3774904.3792952","title":"Towards Token-Level Text Anomaly Detection","display_name":"Towards Token-Level Text Anomaly Detection","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7152746343","doi":"https://doi.org/10.1145/3774904.3792952"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792952","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792952","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792952","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yang Cao","orcid":"https://orcid.org/0000-0003-2184-4491"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yang Cao","raw_affiliation_strings":["Great Bay University, Dongguan, Guangdong, China and Tsinghua University, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0003-2184-4491","affiliations":[{"raw_affiliation_string":"Great Bay University, Dongguan, Guangdong, China and Tsinghua University, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I3131625388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133280158","display_name":"Bicheng Yu","orcid":"https://orcid.org/0009-0009-8263-4480"},"institutions":[{"id":"https://openalex.org/I4210102541","display_name":"Shenzhen Bay Laboratory","ror":"https://ror.org/00sdcjz77","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210102541"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bicheng Yu","raw_affiliation_strings":["Great Bay University, Dongguan, Guangdong, China and Shenzhen University, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0009-8263-4480","affiliations":[{"raw_affiliation_string":"Great Bay University, Dongguan, Guangdong, China and Shenzhen University, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210102541"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109574497","display_name":"Shuling Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I2799850029","display_name":"Dongguan University of Technology","ror":"https://ror.org/01m8p7q42","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799850029"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sikun Yang","raw_affiliation_strings":["Great Bay University, Dongguan, Guangdong, China and Dongguan Key Laboratory for AI and Dynamical Systems, Dongguan, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-8351-2014","affiliations":[{"raw_affiliation_string":"Great Bay University, Dongguan, Guangdong, China and Dongguan Key Laboratory for AI and Dynamical Systems, Dongguan, Guangdong, China","institution_ids":["https://openalex.org/I2799850029"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ming Liu","orcid":"https://orcid.org/0000-0002-2160-6111"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ming Liu","raw_affiliation_strings":["Deakin University, Melbourne, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2160-6111","affiliations":[{"raw_affiliation_string":"Deakin University, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123487246","display_name":"Yujiu Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujiu Yang","raw_affiliation_strings":["Tsinghua University, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-6427-1024","affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3131625388"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75785657,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8733","last_page":"8736"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.424699991941452,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.424699991941452,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12034","display_name":"Digital and Cyber Forensics","score":0.06129999831318855,"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/T11644","display_name":"Spam and Phishing Detection","score":0.061000000685453415,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.7664999961853027},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5914999842643738},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5821999907493591},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.34360000491142273},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3025999963283539}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7664999961853027},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7437999844551086},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5914999842643738},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5821999907493591},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4602000117301941},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4560999870300293},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4156999886035919},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3174999952316284},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3025999963283539},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2671000063419342},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26100000739097595}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792952","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792952","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792952","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792952","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2250539671","https://openalex.org/W3011594683","https://openalex.org/W3169651898","https://openalex.org/W4226060502","https://openalex.org/W4254182148","https://openalex.org/W4283810514","https://openalex.org/W4414032723"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"significant":[1],"progress":[2],"in":[3,77,116],"text":[4,34,56],"anomaly":[5,40,114],"detection":[6,67],"for":[7,112],"web":[8],"applications":[9],"such":[10],"as":[11],"spam":[12],"filtering":[13],"and":[14,61,63,82,90,121],"fake":[15],"news":[16],"detection,":[17,41],"existing":[18],"methods":[19],"are":[20,35,123],"fundamentally":[21],"limited":[22],"to":[23,27],"document-level":[24],"analysis,":[25],"unable":[26],"identify":[28],"which":[29],"specific":[30],"parts":[31],"of":[32,49],"a":[33,42,65],"anomalous.":[36],"We":[37,53],"introduce":[38],"token-level":[39,94],"novel":[43],"paradigm":[44],"that":[45,69,99],"enables":[46],"fine-grained":[47],"localization":[48,115],"anomalies":[50,57],"within":[51],"text.":[52,117],"formally":[54],"define":[55],"at":[58],"both":[59],"document":[60],"token-levels,":[62],"propose":[64],"unified":[66],"framework":[68,101],"operates":[70],"across":[71],"multiple":[72],"levels.":[73],"To":[74],"facilitate":[75],"research":[76],"this":[78],"direction,":[79],"we":[80],"collect":[81],"annotate":[83],"three":[84],"benchmark":[85],"datasets":[86],"spanning":[87],"spam,":[88],"reviews":[89],"grammar":[91],"errors":[92],"with":[93],"labels.":[95],"Experimental":[96],"results":[97],"demonstrate":[98],"our":[100],"achieves":[102],"better":[103],"performance":[104],"than":[105],"other":[106],"6":[107],"baselines,":[108],"opening":[109],"new":[110],"possibilities":[111],"precise":[113],"All":[118],"the":[119],"codes":[120],"data":[122],"publicly":[124],"available":[125],"on":[126],"https://github.com/charles-cao/TokenCore.":[127]},"counts_by_year":[],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2026-04-10T00:00:00"}