{"id":"https://openalex.org/W4412378034","doi":"https://doi.org/10.1145/3726302.3730213","title":"In a Few Words: Comparing Weak Supervision and LLMs for Short Query Intent Classification","display_name":"In a Few Words: Comparing Weak Supervision and LLMs for Short Query Intent Classification","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412378034","doi":"https://doi.org/10.1145/3726302.3730213"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730213","doi":"https://doi.org/10.1145/3726302.3730213","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730213","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730213","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730213","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058105921","display_name":"Daria Alexander","orcid":"https://orcid.org/0000-0001-9478-7083","observed_orcids":["https://orcid.org/0000-0001-9478-7083"]},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Daria Alexander","raw_affiliation_strings":["Radboud University, Nijmegen, Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-9478-7083","affiliations":[{"raw_affiliation_string":"Radboud University, Nijmegen, Netherlands","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060259737","display_name":"Arjen P. de Vries","orcid":"https://orcid.org/0000-0002-2888-4202","observed_orcids":["https://orcid.org/0000-0002-2888-4202"]},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Arjen P. de Vries","raw_affiliation_strings":["Radboud University, Nijmegen, Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-2888-4202","affiliations":[{"raw_affiliation_string":"Radboud University, Nijmegen, Netherlands","institution_ids":["https://openalex.org/I145872427"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145872427"],"apc_list":null,"apc_paid":null,"fwci":2.3323,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88894066,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2977","last_page":"2981"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9940999746322632,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9940999746322632,"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/T10028","display_name":"Topic Modeling","score":0.002899999963119626,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.0007999999797903001,"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/user-intent-classification","display_name":"user intent classification","score":0.9629999995231628},{"id":"https://openalex.org/keywords/short-queries","display_name":"short queries","score":0.7549999952316284},{"id":"https://openalex.org/keywords/weakly-supervised-learning","display_name":"weakly supervised learning","score":0.9570000171661377},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.921999990940094},{"id":"https://openalex.org/keywords/llama-3-1","display_name":"Llama 3.1","score":0.7900000214576721},{"id":"https://openalex.org/keywords/in-context-learning","display_name":"in-context learning","score":0.8899999856948853},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.9359999895095825},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"information retrieval","score":0.6140000224113464},{"id":"https://openalex.org/keywords/precision-recall-trade-off","display_name":"precision-recall trade-off","score":0.7649999856948853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6434903144836426},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4111482799053192},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3802264332771301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3459452688694}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3726302.3730213","doi":"https://doi.org/10.1145/3726302.3730213","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730213","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730213","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.21398","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.21398","pdf_url":"https://arxiv.org/pdf/2504.21398","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:repository.ubn.ru.nl:2066/321408","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/2066/321408","pdf_url":"https://repository.ubn.ru.nl//bitstream/handle/2066/321408/321408.pdf","source":{"id":"https://openalex.org/S4306401067","display_name":"Radboud Repository (Radboud University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I145872427","host_organization_name":"Radboud University Nijmegen","host_organization_lineage":["https://openalex.org/I145872427"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article in monograph or in proceedings"},{"id":"doi:10.48550/arxiv.2504.21398","doi":"https://doi.org/10.48550/arxiv.2504.21398","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.21398","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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:10.1145/3726302.3730213","doi":"https://doi.org/10.1145/3726302.3730213","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730213","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730213","source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2303391636","display_name":null,"funder_award_id":"101070014","funder_id":"https://openalex.org/F4320334322","funder_display_name":"HORIZON EUROPE Framework Programme"},{"id":"https://openalex.org/G7504899342","display_name":"Piloting a Cooperative Open Web Search Infrastructure to Support Europe's Digital Sovereignty","funder_award_id":"101070014","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412378034.pdf","grobid_xml":"https://content.openalex.org/works/W4412378034.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1982858363","https://openalex.org/W2033112710","https://openalex.org/W2049138784","https://openalex.org/W2104217798","https://openalex.org/W2951292886","https://openalex.org/W3034334126","https://openalex.org/W4284689799","https://openalex.org/W4288400169","https://openalex.org/W4388132131","https://openalex.org/W4390404362","https://openalex.org/W4392560653","https://openalex.org/W4399282867","https://openalex.org/W4400526036","https://openalex.org/W4404573983","https://openalex.org/W4412376859","https://openalex.org/W6602430550","https://openalex.org/W7133183334"],"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":{"User":[0],"intent":[1,58],"classification":[2,49,59],"is":[3],"an":[4,88],"important":[5],"task":[6],"in":[7,106],"information":[8],"retrieval.":[9],"Previously,":[10],"user":[11,36,57],"intents":[12],"were":[13],"classified":[14],"manually":[15],"and":[16,63,69,75,80],"automatically;":[17],"the":[18,42,116],"latter":[19],"helped":[20],"to":[21,87,110,121],"avoid":[22],"hand":[23],"labelling":[24],"of":[25,44],"large":[26],"datasets.":[27],"Recent":[28],"studies":[29],"explored":[30],"whether":[31],"LLMs":[32,47,102],"can":[33],"reliably":[34],"determine":[35],"intent.":[37],"However,":[38],"researchers":[39],"have":[40],"recognized":[41],"limitations":[43],"using":[45,66,93],"generative":[46],"for":[48,77,82,118],"tasks.":[50],"In":[51],"this":[52],"study,":[53],"we":[54,72],"empirically":[55],"compare":[56],"into":[60],"informational,":[61],"navigational,":[62],"transactional":[64],"categories,":[65],"weak":[67,94,104],"supervision":[68,95,105],"LLMs.":[70],"Specifically,":[71],"evaluate":[73],"LLaMA-3.1-8B-Instruct":[74,81],"LLaMA-3.1-70B-Instruct":[76],"in-context":[78],"learning":[79],"fine-tuning,":[83],"comparing":[84],"their":[85],"performance":[86],"established":[89],"baseline":[90],"classifier":[91],"trained":[92],"(ORCAS-I).":[96],"Our":[97],"results":[98],"indicate":[99],"that":[100],"while":[101],"outperform":[103],"recall,":[107],"they":[108],"continue":[109],"struggle":[111],"with":[112],"precision,":[113],"which":[114],"shows":[115],"need":[117],"improved":[119],"methods":[120],"balance":[122],"both":[123],"metrics":[124],"effectively.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}