{"id":"https://openalex.org/W4402502151","doi":"https://doi.org/10.48550/arxiv.2408.09439","title":"Towards Boosting LLMs-driven Relevance Modeling with Progressive Retrieved Behavior-augmented Prompting","display_name":"Towards Boosting LLMs-driven Relevance Modeling with Progressive Retrieved Behavior-augmented Prompting","publication_year":2024,"publication_date":"2024-08-18","ids":{"openalex":"https://openalex.org/W4402502151","doi":"https://doi.org/10.48550/arxiv.2408.09439"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2408.09439","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.09439","pdf_url":"https://arxiv.org/pdf/2408.09439","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.09439","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101631516","display_name":"Zeyuan Chen","orcid":"https://orcid.org/0000-0002-0286-6196"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chen, Zeyuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112435473","display_name":"Haiyan Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Haiyan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057019623","display_name":"Kaixin Wu","orcid":"https://orcid.org/0009-0005-1592-8607"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Kaixin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115595744","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0002-0113-2596"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107746253","display_name":"Mingjie Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Mingjie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108167740","display_name":"Jia Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Jia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100656953","display_name":"Zhongyi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhongyi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100441571","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-1613-9256"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wei","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101631516"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9879000186920166,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9879000186920166,"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":0.9876999855041504,"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/T10028","display_name":"Topic Modeling","score":0.9833999872207642,"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/boosting","display_name":"Boosting (machine learning)","score":0.8242428302764893},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.7046011686325073},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3926194906234741},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.28144824504852295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2353130578994751}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8242428302764893},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.7046011686325073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3926194906234741},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.28144824504852295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2353130578994751},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2408.09439","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.09439","pdf_url":"https://arxiv.org/pdf/2408.09439","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2408.09439","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2408.09439","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.09439","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.09439","pdf_url":"https://arxiv.org/pdf/2408.09439","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402502151.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W4231274751","https://openalex.org/W1549363203","https://openalex.org/W2154063878","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W1538046993"],"abstract_inverted_index":{"Relevance":[0],"modeling":[1,197],"is":[2,52],"a":[3,69,75,148,213],"critical":[4],"component":[5],"for":[6,155,195,233],"enhancing":[7],"user":[8,87],"experience":[9],"in":[10,54,90,104,119,180,238],"search":[11,91,99,113,157,174],"engines,":[12],"with":[13,22,140,160,216],"the":[14,30,48,66,105,124,129,136,166,172,206,209,234],"primary":[15],"objective":[16],"of":[17,47,68,108,126,131,208,219,236],"identifying":[18],"items":[19,36],"that":[20,184,203],"align":[21],"users'":[23,97],"queries.":[24],"Traditional":[25],"models":[26],"only":[27],"rely":[28],"on":[29,242],"semantic":[31,76],"congruence":[32],"between":[33],"queries":[34],"and":[35,51,71,135,246],"to":[37,93,110,176,187],"ascertain":[38],"relevance.":[39],"However,":[40],"this":[41,83],"approach":[42],"represents":[43],"merely":[44],"one":[45],"aspect":[46],"relevance":[49,67,81,121,196,239],"judgement,":[50],"insufficient":[53],"isolation.":[55],"Even":[56],"powerful":[57],"Large":[58],"Language":[59],"Models":[60],"(LLMs)":[61],"still":[62],"cannot":[63],"accurately":[64],"judge":[65],"query":[70],"an":[72,132,228],"item":[73],"from":[74,171],"perspective.":[77],"To":[78],"augment":[79],"LLMs-driven":[80],"modeling,":[82],"study":[84],"proposes":[85],"leveraging":[86],"interactions":[88],"recorded":[89],"logs":[92,175],"yield":[94],"insights":[95],"into":[96],"implicit":[98],"intentions.":[100],"The":[101],"challenge":[102],"lies":[103],"effective":[106],"prompting":[107,201],"LLMs":[109,161,194,237],"capture":[111],"dynamic":[112],"intentions,":[114],"which":[115],"poses":[116],"several":[117],"obstacles":[118],"real-world":[120,243],"scenarios,":[122],"i.e.,":[123],"absence":[125],"domain-specific":[127,178],"knowledge,":[128],"inadequacy":[130],"isolated":[133],"prompt,":[134],"prohibitive":[137],"costs":[138],"associated":[139],"deploying":[141],"LLMs.":[142],"In":[143],"response,":[144],"we":[145,164,192,225],"propose":[146],"ProRBP,":[147],"novel":[149],"Progressive":[150],"Retrieved":[151],"Behavior-augmented":[152],"Prompting":[153],"framework":[154,231],"integrating":[156],"scenario-oriented":[158],"knowledge":[159,179],"effectively.":[162],"Specifically,":[163],"perform":[165],"user-driven":[167],"behavior":[168],"neighbors":[169],"retrieval":[170],"daily":[173],"obtain":[177],"time,":[181],"retrieving":[182],"candidates":[183],"users":[185],"consider":[186],"meet":[188],"their":[189],"expectations.":[190],"Then,":[191],"guide":[193],"by":[198,212],"employing":[199],"advanced":[200],"techniques":[202],"progressively":[204],"improve":[205],"outputs":[207],"LLMs,":[210],"followed":[211],"progressive":[214],"aggregation":[215],"comprehensive":[217],"consideration":[218],"diverse":[220],"aspects.":[221],"For":[222],"online":[223,247],"serving,":[224],"have":[226],"developed":[227],"industrial":[229],"application":[230],"tailored":[232],"deployment":[235],"modeling.":[240],"Experiments":[241],"industry":[244],"data":[245],"A/B":[248],"testing":[249],"demonstrate":[250],"our":[251],"proposal":[252],"achieves":[253],"promising":[254],"performance.":[255]},"counts_by_year":[],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2024-09-13T00:00:00"}