{"id":"https://openalex.org/W4401863537","doi":"https://doi.org/10.1145/3637528.3671638","title":"Enhancing Personalized Headline Generation via Offline Goal-conditioned Reinforcement Learning with Large Language Models","display_name":"Enhancing Personalized Headline Generation via Offline Goal-conditioned Reinforcement Learning with Large Language Models","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401863537","doi":"https://doi.org/10.1145/3637528.3671638"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671638","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102869238","display_name":"Xiaoyu Tan","orcid":"https://orcid.org/0000-0003-3555-7143"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoyu Tan","raw_affiliation_strings":["INF Technology (Shanghai) Co., Ltd., Shanghai, China"],"affiliations":[{"raw_affiliation_string":"INF Technology (Shanghai) Co., Ltd., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103325266","display_name":"Leijun Cheng","orcid":"https://orcid.org/0009-0003-6625-1961"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leijun Cheng","raw_affiliation_strings":["School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007950680","display_name":"Xihe Qiu","orcid":"https://orcid.org/0000-0003-4024-925X"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihe Qiu","raw_affiliation_strings":["School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027743711","display_name":"Shaojie Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaojie Shi","raw_affiliation_strings":["School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101941144","display_name":"Yuan Cheng","orcid":"https://orcid.org/0000-0003-2502-9101"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuan Cheng","raw_affiliation_strings":["AI3 Institute, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"AI3 Institute, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055732061","display_name":"Wei Chu","orcid":"https://orcid.org/0000-0002-6401-6111"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Chu","raw_affiliation_strings":["INF Technology (Shanghai) Co., Ltd., Shanghai, China"],"affiliations":[{"raw_affiliation_string":"INF Technology (Shanghai) Co., Ltd., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100579456","display_name":"Yinghui Xu","orcid":"https://orcid.org/0009-0002-7346-2794"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yinghui Xu","raw_affiliation_strings":["AI3 Institute, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"AI3 Institute, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101723187","display_name":"Qi Yuan","orcid":"https://orcid.org/0009-0002-9377-5755"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuan Qi","raw_affiliation_strings":["AI3 Institute, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"AI3 Institute, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100579456","https://openalex.org/A5101723187","https://openalex.org/A5101941144"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":1.0425,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80656264,"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":"5762","last_page":"5772"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9987999796867371,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9894000291824341,"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/headline","display_name":"Headline","score":0.8276343941688538},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7201188206672668},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.7001078724861145},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6408685445785522},{"id":"https://openalex.org/keywords/personalized-learning","display_name":"Personalized learning","score":0.4554124176502228},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43563586473464966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43193328380584717},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09698697924613953},{"id":"https://openalex.org/keywords/teaching-method","display_name":"Teaching method","score":0.08920112252235413},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.0870864987373352}],"concepts":[{"id":"https://openalex.org/C2778689934","wikidata":"https://www.wikidata.org/wiki/Q1313396","display_name":"Headline","level":2,"score":0.8276343941688538},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7201188206672668},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.7001078724861145},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6408685445785522},{"id":"https://openalex.org/C142039133","wikidata":"https://www.wikidata.org/wiki/Q3620943","display_name":"Personalized learning","level":5,"score":0.4554124176502228},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43563586473464966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43193328380584717},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09698697924613953},{"id":"https://openalex.org/C88610354","wikidata":"https://www.wikidata.org/wiki/Q1813494","display_name":"Teaching method","level":2,"score":0.08920112252235413},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0870864987373352},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C51672120","wikidata":"https://www.wikidata.org/wiki/Q303446","display_name":"Cooperative learning","level":3,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C15122004","wikidata":"https://www.wikidata.org/wiki/Q385756","display_name":"Open learning","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3671638","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2081265723","https://openalex.org/W2251374538","https://openalex.org/W2561360547","https://openalex.org/W2735492478","https://openalex.org/W2741438349","https://openalex.org/W2759083144","https://openalex.org/W2914949666","https://openalex.org/W2946343014","https://openalex.org/W2950421571","https://openalex.org/W2964008635","https://openalex.org/W2964044287","https://openalex.org/W2971200279","https://openalex.org/W3023371261","https://openalex.org/W3176778415","https://openalex.org/W3207924272","https://openalex.org/W4221143046","https://openalex.org/W4226278401","https://openalex.org/W4287674181","https://openalex.org/W4385564993","https://openalex.org/W4392796555","https://openalex.org/W6782465632"],"related_works":["https://openalex.org/W4285135530","https://openalex.org/W2380567098","https://openalex.org/W2035489689","https://openalex.org/W906669285","https://openalex.org/W1553197492","https://openalex.org/W85886512","https://openalex.org/W1586468330","https://openalex.org/W1514610457","https://openalex.org/W3173716828","https://openalex.org/W2515595154"],"abstract_inverted_index":{"Recently,":[0],"significant":[1],"advancements":[2],"have":[3,35],"been":[4],"made":[5],"in":[6,27,45,68],"Large":[7],"Language":[8],"Models":[9],"(LLMs)":[10],"through":[11],"the":[12,36,46,117,150,156,164,169,172,180,184],"implementation":[13],"of":[14,48,174,186],"various":[15],"alignment":[16],"techniques.":[17],"These":[18],"techniques":[19],"enable":[20],"LLMs":[21,34,53,89,187],"to":[22,29,38,83,112,188],"generate":[23,84,141,189],"highly":[24],"tailored":[25],"content":[26,49],"response":[28],"diverse":[30],"user":[31,55],"instructions.":[32],"Consequently,":[33],"potential":[37],"serve":[39],"as":[40,152],"robust,":[41],"customizable":[42],"recommendation":[43],"systems":[44],"field":[47],"recommendation.":[50],"However,":[51],"using":[52,88,104],"with":[54,90,193],"individual":[56],"information":[57],"and":[58,125,138],"online":[59,92,108,160],"exploration":[60,109,161],"remains":[61],"a":[62,80,153],"challenge,":[63],"which":[64],"are":[65],"important":[66],"perspectives":[67],"developing":[69],"personalized":[70,85,142],"news":[71,86,191],"headline":[72],"generation":[73],"algorithms.":[74],"In":[75],"this":[76,177],"paper,":[77],"we":[78],"propose":[79],"novel":[81],"framework":[82,131],"headlines":[87,143,192],"extensive":[91],"exploration.":[93],"The":[94],"proposed":[95],"approach":[96],"involves":[97],"initially":[98],"training":[99,119],"an":[100],"offline":[101],"goal-conditioned":[102,154,194],"policy":[103],"supervised":[105,198],"learning.":[106],"Subsequently,":[107],"is":[110],"employed":[111],"collect":[113],"new":[114],"data":[115],"for":[116],"next":[118],"iteration.":[120],"Results":[121],"from":[122],"simulations,":[123],"experiments,":[124],"real-word":[126],"scenario":[127],"demonstrate":[128],"that":[129],"our":[130,175],"achieves":[132],"outstanding":[133],"performance":[134],"on":[135],"established":[136],"benchmarks":[137],"can":[139,158],"effectively":[140],"under":[144],"different":[145],"reward":[146],"settings.":[147],"By":[148],"treating":[149],"LLM":[151],"agent,":[155],"model":[157],"perform":[159],"by":[162],"modifying":[163],"goals":[165],"without":[166],"frequently":[167],"retraining":[168],"model.":[170],"To":[171],"best":[173],"knowledge,":[176],"work":[178],"represents":[179],"first":[181],"investigation":[182],"into":[183],"capability":[185],"customized":[190],"reinforcement":[195],"learning":[196,199],"via":[197],"within":[200],"LLMs.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}