{"id":"https://openalex.org/W4412877014","doi":"https://doi.org/10.1145/3711896.3737222","title":"FoodGPT: Reinforcement Post-Training of Large Language Models in the Food Delivery Domain","display_name":"FoodGPT: Reinforcement Post-Training of Large Language Models in the Food Delivery Domain","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412877014","doi":"https://doi.org/10.1145/3711896.3737222"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3737222","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737222","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737222","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","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/10.1145/3711896.3737222","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiang Wang","orcid":"https://orcid.org/0009-0002-2399-1153"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiang Wang","raw_affiliation_strings":["Rajax Network Technology (ele.me), Alibaba Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-2399-1153","affiliations":[{"raw_affiliation_string":"Rajax Network Technology (ele.me), Alibaba Group, Shanghai, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114218453","display_name":"Zhengxin Dong","orcid":"https://orcid.org/0009-0002-1921-3340"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengxin Dong","raw_affiliation_strings":["Rajax Network Technology (ele.me), Alibaba Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-1921-3340","affiliations":[{"raw_affiliation_string":"Rajax Network Technology (ele.me), Alibaba Group, Shanghai, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bing Bai","orcid":"https://orcid.org/0009-0007-6508-8399"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Bai","raw_affiliation_strings":["Rajax Network Technology (ele.me), Alibaba Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-6508-8399","affiliations":[{"raw_affiliation_string":"Rajax Network Technology (ele.me), Alibaba Group, Shanghai, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039634918","display_name":"Guyu Jiang","orcid":"https://orcid.org/0009-0003-8997-2585"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guyu Jiang","raw_affiliation_strings":["Rajax Network Technology (ele.me), Alibaba Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-8997-2585","affiliations":[{"raw_affiliation_string":"Rajax Network Technology (ele.me), Alibaba Group, Shanghai, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111299538","display_name":"Aiquan Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aiquan Yuan","raw_affiliation_strings":["Rajax Network Technology (ele.me), Alibaba Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-5372-6086","affiliations":[{"raw_affiliation_string":"Rajax Network Technology (ele.me), Alibaba Group, Shanghai, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101449530","display_name":"Guodong Cao","orcid":"https://orcid.org/0009-0000-0742-607X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guodong Cao","raw_affiliation_strings":["Rajax Network Technology (ele.me), Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-0742-607X","affiliations":[{"raw_affiliation_string":"Rajax Network Technology (ele.me), Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09116362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4966","last_page":"4974"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9969000220298767,"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":0.9969000220298767,"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":0.9629999995231628,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9467999935150146,"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/computer-science","display_name":"Computer science","score":0.6859318017959595},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5329490900039673},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5151509046554565},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.45381516218185425},{"id":"https://openalex.org/keywords/food-delivery","display_name":"Food delivery","score":0.42110657691955566},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36415618658065796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3517715334892273},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14856526255607605},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08167457580566406}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6859318017959595},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5329490900039673},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5151509046554565},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.45381516218185425},{"id":"https://openalex.org/C2994309678","wikidata":"https://www.wikidata.org/wiki/Q10932402","display_name":"Food delivery","level":2,"score":0.42110657691955566},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36415618658065796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3517715334892273},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14856526255607605},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08167457580566406},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3737222","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737222","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737222","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3711896.3737222","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737222","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737222","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412877014.pdf","grobid_xml":"https://content.openalex.org/works/W4412877014.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2989224055","https://openalex.org/W2990138404","https://openalex.org/W3034828204","https://openalex.org/W3173727191","https://openalex.org/W3177219148","https://openalex.org/W4388329494","https://openalex.org/W4393160809","https://openalex.org/W4393161145","https://openalex.org/W6604032921"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W2766950319"],"abstract_inverted_index":{"On-demand":[0],"Food":[1],"Delivery":[2],"(OFD)":[3],"platforms,":[4],"such":[5,123],"as":[6,124],"Ele.me":[7],"and":[8,26,49,69,92,128,136,161],"Meituan,":[9],"have":[10],"transformed":[11],"daily":[12],"life":[13],"by":[14],"offering":[15],"convenient":[16],"ordering":[17],"services.":[18],"However,":[19],"challenges":[20],"remain":[21],"in":[22,36,158,165,169],"understanding":[23],"user":[24,166],"intentions":[25],"processing":[27],"product-related":[28],"text":[29],"information.":[30],"Existing":[31],"NLP":[32,67],"models,":[33,122],"while":[34,111],"advanced":[35],"general":[37,121],"tasks,":[38,68,132],"are":[39,177],"less":[40],"effective":[41],"for":[42],"OFD-specific":[43],"needs":[44],"due":[45],"to":[46],"data":[47,135],"scarcity":[48],"high":[50],"computational":[51],"costs.":[52],"This":[53],"paper":[54],"introduces":[55],"FoodInstruct,":[56],"a":[57,71,155,162],"Chinese":[58],"dataset":[59],"with":[60,97],"1.6":[61],"million":[62],"examples":[63],"across":[64,145],"12":[65],"OFD-related":[66],"FoodGPT,":[70,107],"domain-specific":[72],"large":[73],"language":[74],"model.":[75],"We":[76],"propose":[77],"an":[78,98],"efficient":[79],"reinforcement":[80],"post-training":[81],"framework":[82],"that":[83,118],"combines":[84],"Supervised":[85],"Fine-Tuning":[86],"(SFT),":[87],"Direct":[88],"Preference":[89],"Optimization":[90,95],"(DPO),":[91],"Proximal":[93],"Policy":[94],"(PPO)":[96],"additional":[99],"rule-based":[100],"reward":[101],"signal.":[102],"The":[103,139,174],"resulting":[104],"foundation":[105],"model,":[106],"enhances":[108],"model":[109,140],"performance":[110],"minimizing":[112],"resource":[113],"consumption.":[114],"Experimental":[115],"results":[116],"demonstrate":[117],"FoodGPT":[119],"outperforms":[120],"Qwen":[125],"2.5,":[126],"Llama3.1":[127],"DeepSeek-LLM,":[129],"on":[130],"OFD":[131],"using":[133],"fewer":[134],"training":[137],"iterations.":[138],"has":[141],"already":[142],"been":[143],"deployed":[144],"numerous":[146],"applications":[147],"within":[148],"the":[149,170],"company.":[150],"For":[151],"instance,":[152],"it":[153],"achieved":[154],"0.57%":[156],"increase":[157,164],"click-through":[159],"rate":[160,168],"0.32%":[163],"visit-to-purchase":[167],"ITG":[171],"online":[172],"experiment.":[173],"core":[175],"contributions":[176],"now":[178],"publicly":[179],"accessible":[180],"at":[181],"https://huggingface.co/elemenlp.":[182]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}