{"id":"https://openalex.org/W4416956371","doi":"https://doi.org/10.1145/3770854.3783917","title":"Optimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Search","display_name":"Optimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Search","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W4416956371","doi":"https://doi.org/10.1145/3770854.3783917"},"language":null,"primary_location":{"id":"doi:10.1145/3770854.3783917","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3783917","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 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3770854.3783917","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035288094","display_name":"Ziyang Zeng","orcid":"https://orcid.org/0009-0008-3429-9668"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Zeng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-8773-7301","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065760141","display_name":"Heming Jing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heming Jing","raw_affiliation_strings":["Xiaohongshu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9216-7032","affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027751401","display_name":"Jindong Chen","orcid":"https://orcid.org/0000-0002-7841-9608"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jindong Chen","raw_affiliation_strings":["Xiaohongshu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-2977-398X","affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016569030","display_name":"Xiangli Li","orcid":"https://orcid.org/0000-0001-8753-2402"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangli Li","raw_affiliation_strings":["Xiaohongshu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0126-932X","affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongyu Liu","orcid":"https://orcid.org/0009-0001-8009-5112"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongyu Liu","raw_affiliation_strings":["Xiaohongshu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-8009-5112","affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100312043","display_name":"Yixuan He","orcid":"https://orcid.org/0009-0001-9832-9028"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixuan He","raw_affiliation_strings":["Xiaohongshu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-0566-0622","affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067705006","display_name":"Zhengyu Li","orcid":"https://orcid.org/0000-0002-0352-1675"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengyu Li","raw_affiliation_strings":["Xiaohongshu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2836-276X","affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019640816","display_name":"Yige Sun","orcid":"https://orcid.org/0000-0001-8661-8642"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yige Sun","raw_affiliation_strings":["Xiaohongshu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-3025-2142","affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037938574","display_name":"Zheyong Xie","orcid":"https://orcid.org/0009-0009-7453-5781"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheyong Xie","raw_affiliation_strings":["Xiaohongshu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-7453-5781","affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050042610","display_name":"Yuqing Yang","orcid":"https://orcid.org/0000-0002-2110-9318"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqing Yang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5333-1346","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003340183","display_name":"Shaosheng Cao","orcid":"https://orcid.org/0000-0002-3795-8824"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaosheng Cao","raw_affiliation_strings":["Xiaohongshu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3795-8824","affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101866323","display_name":"Jun Fan","orcid":"https://orcid.org/0009-0000-2127-0702"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Fan","raw_affiliation_strings":["Xiaohongshu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-2127-0702","affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yi Wu","orcid":"https://orcid.org/0009-0007-8838-2785"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Wu","raw_affiliation_strings":["Xiaohongshu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-8838-2785","affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057257043","display_name":"Yao Hu","orcid":"https://orcid.org/0000-0002-0199-6044"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao Hu","raw_affiliation_strings":["Xiaohongshu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-1274-7111","affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01640724,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2551","last_page":"2561"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.8199999928474426,"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":0.8199999928474426,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.024800000712275505,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.0215000007301569,"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/relevance","display_name":"Relevance (law)","score":0.8497999906539917},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.8375999927520752},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5058000087738037},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.48899999260902405},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4350000023841858},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.40209999680519104},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.39899998903274536}],"concepts":[{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.8497999906539917},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8375999927520752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7020000219345093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6269000172615051},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6065999865531921},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5058000087738037},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.48899999260902405},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4350000023841858},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40209999680519104},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.39899998903274536},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.319599986076355},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3770854.3783917","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3783917","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 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.00968","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.00968","pdf_url":"https://arxiv.org/pdf/2512.00968","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,"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.00968","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.00968","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,"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:10.1145/3770854.3783917","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3783917","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 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Ranking":[0],"relevance":[1,22,31,41,66,126,156,222],"is":[2],"a":[3,17,132,137,170,197],"fundamental":[4],"task":[5,134],"in":[6,47,65,118,128],"search":[7,130,203,235],"engines,":[8],"aiming":[9],"to":[10,16,92,100,110,143,196],"identify":[11],"the":[12,37,112,145,159,192],"items":[13],"most":[14],"relevant":[15],"given":[18],"user":[19],"query.":[20],"Traditional":[21],"models":[23],"typically":[24],"produce":[25],"scalar":[26],"scores":[27],"or":[28,85],"directly":[29],"predict":[30],"labels,":[32],"limiting":[33,107],"both":[34,61],"interpretability":[35,62],"and":[36,63,104,114,135,164,208,223,230],"modeling":[38,127],"of":[39,83,149,178],"complex":[40,52],"signals.":[42],"Inspired":[43],"by":[44],"recent":[45],"advances":[46],"Chain-of-Thought":[48],"(CoT)":[49],"reasoning":[50,58,98,133,147,161],"for":[51,201,232],"tasks,":[53],"we":[54,124,152,189],"investigate":[55],"whether":[56],"explicit":[57],"can":[59],"enhance":[60,144],"performance":[64],"modeling.":[67],"However,":[68],"existing":[69],"reasoning-based":[70],"Generative":[71],"Relevance":[72],"Models":[73],"(GRMs)":[74],"primarily":[75],"rely":[76],"on":[77,80],"supervised":[78],"fine-tuning":[79],"large":[81],"amounts":[82],"human-annotated":[84],"synthetic":[86],"CoT":[87],"data,":[88],"which":[89,174],"often":[90],"leads":[91],"limited":[93],"generalization.":[94],"Moreover,":[95],"domain-agnostic,":[96],"free-form":[97],"tends":[99],"be":[101],"overly":[102],"generic":[103],"insufficiently":[105],"grounded,":[106],"its":[108,227],"potential":[109],"handle":[111],"diverse":[113],"ambiguous":[115],"cases":[116],"prevalent":[117],"open-domain":[119],"search.":[120],"In":[121],"this":[122],"work,":[123],"formulate":[125],"Xiaohongshu":[129],"as":[131],"introduce":[136],"Reinforcement":[138],"Learning":[139],"(RL)-based":[140],"training":[141],"framework":[142],"grounded":[146],"capabilities":[148],"GRMs.":[150],"Specifically,":[151],"incorporate":[153],"practical":[154],"business-specific":[155],"criteria":[157,180],"into":[158],"multi-step":[160],"prompt":[162],"design":[163],"propose":[165],"Stepwise":[166],"Advantage":[167],"Masking":[168],"(SAM),":[169],"lightweight":[171,198],"process-supervision":[172],"strategy":[173],"facilitates":[175],"effective":[176],"learning":[177],"these":[179],"through":[181],"improved":[182],"credit":[183],"assignment.":[184],"To":[185],"enable":[186],"industrial":[187,234],"deployment,":[188],"further":[190],"distill":[191],"large-scale":[193,233],"RL-tuned":[194],"model":[195],"version":[199],"suitable":[200],"real-world":[202],"systems.":[204,236],"Extensive":[205],"offline":[206],"evaluations":[207],"online":[209],"A/B":[210],"tests":[211],"demonstrate":[212],"that":[213],"our":[214],"approach":[215],"consistently":[216],"delivers":[217],"significant":[218],"improvements":[219],"across":[220],"key":[221],"business":[224],"metrics,":[225],"validating":[226],"effectiveness,":[228],"robustness,":[229],"practicality":[231]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-12-03T00:00:00"}