{"id":"https://openalex.org/W4412877209","doi":"https://doi.org/10.1145/3711896.3737602","title":"Practical Guidance and Tutorial on Incentivizing Reasoning in LLMs using Distillation and Reinforcement Learning","display_name":"Practical Guidance and Tutorial on Incentivizing Reasoning in LLMs using Distillation and Reinforcement Learning","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412877209","doi":"https://doi.org/10.1145/3711896.3737602"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3737602","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737602","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737602","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/10.1145/3711896.3737602","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101523508","display_name":"Zhaopeng Qiu","orcid":"https://orcid.org/0009-0006-7067-3763"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaopeng Qiu","raw_affiliation_strings":["NVIDIA, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-7067-3763","affiliations":[{"raw_affiliation_string":"NVIDIA, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingqi Zhang","orcid":"https://orcid.org/0009-0009-0213-3871"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingqi Zhang","raw_affiliation_strings":["NVIDIA, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-0213-3871","affiliations":[{"raw_affiliation_string":"NVIDIA, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060749739","display_name":"Shuang Yu","orcid":"https://orcid.org/0009-0002-6827-0392"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuang Yu","raw_affiliation_strings":["NVIDIA, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-6827-0392","affiliations":[{"raw_affiliation_string":"NVIDIA, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuai Zhang","orcid":"https://orcid.org/0009-0007-1929-161X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai Zhang","raw_affiliation_strings":["NVIDIA, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-1929-161X","affiliations":[{"raw_affiliation_string":"NVIDIA, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103287856","display_name":"Junjie Lai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junjie Lai","raw_affiliation_strings":["NVIDIA, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-0598-9375","affiliations":[{"raw_affiliation_string":"NVIDIA, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30057389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6249","last_page":"6250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11938","display_name":"ERP Systems Implementation and Impact","score":0.5834000110626221,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11938","display_name":"ERP Systems Implementation and Impact","score":0.5834000110626221,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10763","display_name":"Digital Transformation in Industry","score":0.554099977016449,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12594","display_name":"Collaboration in agile enterprises","score":0.5527999997138977,"subfield":{"id":"https://openalex.org/subfields/1405","display_name":"Management of Technology and Innovation"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7568378448486328},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6079093813896179},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5733543634414673},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.509442150592804},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4539579451084137},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14280307292938232},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.1413431167602539},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06528493762016296},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.05548596382141113}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7568378448486328},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6079093813896179},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5733543634414673},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.509442150592804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4539579451084137},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14280307292938232},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1413431167602539},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06528493762016296},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.05548596382141113}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3737602","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737602","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737602","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:10.1145/3711896.3737602","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737602","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737602","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412877209.pdf","grobid_xml":"https://content.openalex.org/works/W4412877209.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4406231568"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"With":[0],"reasoning":[1,43,55,69,125],"models":[2,32,56,73],"like":[3,74],"DeepSeek-R1":[4,75],"and":[5,57,82,84,138],"OpenAI's":[6],"o1":[7],"demonstrating":[8],"breakthrough":[9],"capabilities":[10,27,44,70,93,126],"in":[11,18,28,45,121],"complex":[12],"problem-solving,":[13],"there":[14],"is":[15],"growing":[16],"interest":[17],"the":[19,100,105,109],"AI":[20],"community":[21],"about":[22],"how":[23,66,87,122,130],"to":[24,67,123,131,147],"unlock":[25],"similar":[26],"other":[29],"large":[30],"language":[31],"(LLMs).":[33],"This":[34],"hands-on":[35,141],"tutorial":[36],"dives":[37],"into":[38,76,127],"practical":[39,119],"methods":[40],"for":[41,135],"building":[42],"LLMs":[46,78],"through":[47,104],"two":[48],"primary":[49],"approaches:":[50],"knowledge":[51,120],"distillation":[52],"from":[53,71],"advanced":[54],"post-training":[58],"with":[59,118,140],"reinforcement":[60,88],"learning":[61,89],"techniques.":[62],"Participants":[63],"will":[64,102,115],"learn":[65],"transfer":[68],"cutting-edge":[72],"smaller":[77],"such":[79],"as":[80],"Qwen":[81],"Llama,":[83],"then":[85],"explore":[86],"can":[90,144],"take":[91],"these":[92],"even":[94],"further.":[95],"Through":[96],"interactive":[97],"Jupyter":[98],"notebook,":[99],"participants":[101,114],"exercise":[103],"entire":[106],"process.":[107],"By":[108],"end":[110],"of":[111],"this":[112,136],"session,":[113],"be":[116,145],"equipped":[117],"incentivize":[124],"LLMs,":[128],"understand":[129],"use":[132],"various":[133],"frameworks":[134],"task,":[137],"leave":[139],"experience":[142],"that":[143],"applied":[146],"their":[148],"own":[149],"projects.":[150],"The":[151],"related":[152],"materials":[153],"are":[154],"available":[155],"at":[156],"https://zpqiu.github.io/reasoning-model-tutorial-kdd2025.":[157]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}