{"id":"https://openalex.org/W4412876847","doi":"https://doi.org/10.1145/3711896.3737242","title":"LLM4Tag: Automatic Tagging System for Information Retrieval via Large Language Models","display_name":"LLM4Tag: Automatic Tagging System for Information Retrieval via Large Language Models","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412876847","doi":"https://doi.org/10.1145/3711896.3737242"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3737242","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737242","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737242","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 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737242","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054330014","display_name":"Ruiming Tang","orcid":"https://orcid.org/0000-0002-9224-2431"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruiming Tang","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008281909","display_name":"Chenxu Zhu","orcid":"https://orcid.org/0000-0001-8320-6845"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxu Zhu","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427434","display_name":"Bo Chen","orcid":"https://orcid.org/0000-0003-3750-2533"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Chen","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107925083","display_name":"Weipeng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weipeng Zhang","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034417837","display_name":"Menghui Zhu","orcid":"https://orcid.org/0000-0002-8567-2185"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Menghui Zhu","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012370987","display_name":"Xinyi Dai","orcid":"https://orcid.org/0000-0002-3351-5401"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Dai","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019541869","display_name":"Huifeng Guo","orcid":"https://orcid.org/0000-0002-7393-8994"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huifeng Guo","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5054330014"],"corresponding_institution_ids":["https://openalex.org/I2250955327"],"apc_list":null,"apc_paid":null,"fwci":5.4906,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95642264,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4882","last_page":"4890"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9993000030517578,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9952999949455261,"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":0.8301903605461121},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6005347967147827},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5634176135063171},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49856114387512207},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42317402362823486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8301903605461121},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6005347967147827},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5634176135063171},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49856114387512207},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42317402362823486}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3737242","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737242","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737242","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 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3711896.3737242","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737242","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737242","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 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412876847.pdf","grobid_xml":"https://content.openalex.org/works/W4412876847.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1964066675","https://openalex.org/W1978577143","https://openalex.org/W2039074357","https://openalex.org/W2055252587","https://openalex.org/W2070614186","https://openalex.org/W2096130203","https://openalex.org/W2116926073","https://openalex.org/W2883730939","https://openalex.org/W3185880309","https://openalex.org/W3217215940","https://openalex.org/W4309674289","https://openalex.org/W4393160809","https://openalex.org/W6600013530"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Tagging":[0],"systems":[1,28],"play":[2],"an":[3,80],"essential":[4],"role":[5],"in":[6,26,51,58],"various":[7],"information":[8],"retrieval":[9],"applications":[10],"such":[11],"as":[12],"search":[13],"engines":[14],"and":[15,37,64,95,119,152],"recommender":[16],"systems.":[17],"Recently,":[18],"Large":[19],"Language":[20],"Models":[21],"(LLMs)":[22],"have":[23,47],"been":[24,155],"applied":[25],"tagging":[27,82,160],"due":[29],"to":[30,60,93,113,131,161],"their":[31],"extensive":[32],"world":[33],"knowledge,":[34,63],"semantic":[35],"understanding,":[36],"reasoning":[38],"capabilities.":[39],"Despite":[40],"achieving":[41],"remarkable":[42],"performance,":[43],"existing":[44],"methods":[45],"still":[46],"limitations,":[48],"including":[49],"difficulties":[50],"retrieving":[52],"relevant":[53,101],"candidate":[54,102],"tags":[55,116],"comprehensively,":[56],"challenges":[57],"adapting":[59],"emerging":[61],"domain-specific":[62],"the":[65,149],"lack":[66],"of":[67,164,166],"reliable":[68,133],"tag":[69,88,103,108,125,134],"confidence":[70,126,135],"quantification.":[71],"To":[72],"address":[73],"these":[74],"three":[75,140],"limitations":[76],"above,":[77],"we":[78],"propose":[79],"automatic":[81],"system":[83],"LLM4Tag.":[84],"First,":[85],"a":[86,98,106,124],"graph-based":[87],"recall":[89],"module":[90,110,128],"is":[91,111,129],"designed":[92],"effectively":[94],"comprehensively":[96],"construct":[97],"small-scale":[99],"highly":[100],"set.":[104],"Subsequently,":[105],"knowledge-enhanced":[107],"generation":[109],"employed":[112],"generate":[114,132],"accurate":[115],"with":[117],"long-term":[118],"short-term":[120],"knowledge":[121],"injection.":[122],"Finally,":[123],"calibration":[127],"introduced":[130],"scores.":[136],"Extensive":[137],"experiments":[138],"over":[139],"large-scale":[141],"industrial":[142],"datasets":[143],"show":[144],"that":[145],"LLM4Tag":[146,153],"significantly":[147],"outperforms":[148],"state-of-the-art":[150],"baselines":[151],"has":[154],"deployed":[156],"online":[157],"for":[158],"content":[159],"serve":[162],"hundreds":[163],"millions":[165],"users.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}