{"id":"https://openalex.org/W4412376892","doi":"https://doi.org/10.1145/3726302.3730162","title":"Aligning Web Query Generation with Ranking Objectives via Direct Preference Optimization","display_name":"Aligning Web Query Generation with Ranking Objectives via Direct Preference Optimization","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412376892","doi":"https://doi.org/10.1145/3726302.3730162"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730162","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730162","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730162","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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","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/10.1145/3726302.3730162","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103926302","display_name":"Jo\u00e3o Coelho","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jo\u00e3o Coelho","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0009-0001-6207-1934","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055101594","display_name":"Bruno Martins","orcid":"https://orcid.org/0000-0002-3856-2936"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I4387152517","display_name":"Instituto Superior T\u00e9cnico","ror":"https://ror.org/03db2by73","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103","https://openalex.org/I4387152517"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Bruno Martins","raw_affiliation_strings":["Instituto Superior T\u00e9cnico and INESC-ID, Lisbon, Portugal"],"raw_orcid":"https://orcid.org/0000-0002-3856-2936","affiliations":[{"raw_affiliation_string":"Instituto Superior T\u00e9cnico and INESC-ID, Lisbon, Portugal","institution_ids":["https://openalex.org/I121345201","https://openalex.org/I4387152517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002705720","display_name":"Jo\u00e3o Magalh\u00e3es","orcid":"https://orcid.org/0000-0001-6290-5719"},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Magalh\u00e3es","raw_affiliation_strings":["NOVA School of Science and Technology, Lisbon, Portugal"],"raw_orcid":"https://orcid.org/0000-0001-6290-5719","affiliations":[{"raw_affiliation_string":"NOVA School of Science and Technology, Lisbon, Portugal","institution_ids":["https://openalex.org/I83558840"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006340382","display_name":"Chenyan Xiong","orcid":"https://orcid.org/0000-0002-0392-4183"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenyan Xiong","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0392-4183","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103926302"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18701684,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2982","last_page":"2986"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9987999796867371,"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/T11106","display_name":"Data Management and Algorithms","score":0.9987999796867371,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9969000220298767,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9916999936103821,"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/ranking","display_name":"Ranking (information retrieval)","score":0.7754027247428894},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7400720119476318},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.7221591472625732},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.545103132724762},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.5404580235481262},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5112509727478027},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.3208412528038025},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.17437678575515747},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10885262489318848}],"concepts":[{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7754027247428894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7400720119476318},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.7221591472625732},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.545103132724762},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.5404580235481262},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5112509727478027},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.3208412528038025},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17437678575515747},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10885262489318848}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3726302.3730162","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730162","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730162","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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:run.unl.pt:10362/187475","is_oa":true,"landing_page_url":"http://hdl.handle.net/10362/187475","pdf_url":null,"source":{"id":"https://openalex.org/S4306400678","display_name":"Universidade Nova de Lisboa's Repository (Universidade Nova de Lisboa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83558840","host_organization_name":"Universidade Nova de Lisboa","host_organization_lineage":["https://openalex.org/I83558840"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730162","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730162","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730162","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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G927278328","display_name":null,"funder_award_id":"PRT/BD/153683/2021","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320319180","display_name":"Carnegie Mellon Portugal","ror":null},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412376892.pdf","grobid_xml":"https://content.openalex.org/works/W4412376892.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2627491027","https://openalex.org/W3212725701","https://openalex.org/W4224865658","https://openalex.org/W4327644554","https://openalex.org/W4389523765","https://openalex.org/W6600763685"],"related_works":["https://openalex.org/W2931602588","https://openalex.org/W1986265453","https://openalex.org/W2096359267","https://openalex.org/W3125756434","https://openalex.org/W2367099342","https://openalex.org/W2184296057","https://openalex.org/W4256058599","https://openalex.org/W2026738364","https://openalex.org/W2901901036","https://openalex.org/W2362460270"],"abstract_inverted_index":{"Neural":[0],"retrieval":[1,56,107],"models":[2,38,132],"excel":[3],"in":[4,49],"Web":[5,27],"search,":[6],"but":[7],"their":[8],"training":[9,45],"requires":[10],"substantial":[11],"amounts":[12],"of":[13,26],"labeled":[14],"query-document":[15,64,115],"pairs,":[16],"which":[17,51],"are":[18],"costly":[19],"to":[20,53,85,95,120,130],"obtain.":[21],"With":[22],"the":[23,90,98,125],"widespread":[24],"availability":[25],"document":[28],"collections":[29],"like":[30],"ClueWeb22,":[31],"synthetic":[32,44,135],"queries":[33,46,103],"generated":[34],"by":[35],"large":[36],"language":[37],"offer":[39],"a":[40,77],"scalable":[41],"alternative.":[42],"Still,":[43],"often":[47],"vary":[48],"quality,":[50],"leads":[52],"suboptimal":[54],"downstream":[55,106,122],"performance.":[57],"Existing":[58],"methods":[59],"typically":[60],"filter":[61],"out":[62],"noisy":[63],"pairs":[65,116],"based":[66],"on":[67,124],"signals":[68,88],"from":[69],"an":[70],"external":[71],"re-ranker.":[72],"In":[73],"contrast,":[74],"we":[75],"propose":[76],"framework":[78],"that":[79,104],"leverages":[80],"Direct":[81],"Preference":[82],"Optimization":[83],"(DPO)":[84],"integrate":[86],"ranking":[87],"into":[89],"query":[91],"generation":[92],"process,":[93],"aiming":[94],"directly":[96],"optimize":[97],"model":[99],"towards":[100],"generating":[101],"high-quality":[102],"maximize":[105],"effectiveness.":[108],"Experiments":[109],"show":[110],"higher":[111],"ranker-assessed":[112],"relevance":[113],"between":[114],"after":[117],"DPO,":[118],"leading":[119],"stronger":[121],"performance":[123],"MS~MARCO":[126],"benchmark":[127],"when":[128],"compared":[129],"baseline":[131],"trained":[133],"with":[134],"data.":[136]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}