{"id":"https://openalex.org/W4399418772","doi":"https://doi.org/10.1145/3651671.3651737","title":"Distilling Multi-Step Reasoning Capabilities into Smaller Language Model","display_name":"Distilling Multi-Step Reasoning Capabilities into Smaller Language Model","publication_year":2024,"publication_date":"2024-02-02","ids":{"openalex":"https://openalex.org/W4399418772","doi":"https://doi.org/10.1145/3651671.3651737"},"language":"en","primary_location":{"id":"doi:10.1145/3651671.3651737","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3651671.3651737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 16th International Conference on Machine Learning and Computing","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/A5095848529","display_name":"Yauwai Yim","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Yauwai Yim","raw_affiliation_strings":["Hong Kong University of Science and Technology, China"],"raw_orcid":"https://orcid.org/0009-0002-1458-1208","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zirui Wang","orcid":"https://orcid.org/0009-0001-3811-5968"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zirui Wang","raw_affiliation_strings":["Hong Kong University of Science and Technology, China"],"raw_orcid":"https://orcid.org/0009-0001-3811-5968","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5095848529"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":0.3311,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62716311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"530","last_page":"535"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9972000122070312,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9782999753952026,"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/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.888126015663147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7686300277709961},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6808065176010132},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6664249300956726},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6595747470855713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5934203863143921},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.5919630527496338},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4899980127811432},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.45066606998443604},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4160900115966797},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.24081960320472717},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0676141083240509}],"concepts":[{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.888126015663147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7686300277709961},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6808065176010132},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6664249300956726},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6595747470855713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5934203863143921},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.5919630527496338},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4899980127811432},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.45066606998443604},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4160900115966797},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.24081960320472717},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0676141083240509},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3651671.3651737","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3651671.3651737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 16th International Conference on Machine Learning and Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-142405","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-142405","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2924120895","https://openalex.org/W2946609015","https://openalex.org/W2963809228","https://openalex.org/W2981852735","https://openalex.org/W3170224286","https://openalex.org/W3207166518","https://openalex.org/W4287891464","https://openalex.org/W4288089799","https://openalex.org/W4367628242","https://openalex.org/W4377864835","https://openalex.org/W4385571831","https://openalex.org/W4385573504","https://openalex.org/W4385574180","https://openalex.org/W6600388300","https://openalex.org/W6600424091","https://openalex.org/W6604801084","https://openalex.org/W6607643177","https://openalex.org/W6637031373"],"related_works":["https://openalex.org/W3213963881","https://openalex.org/W2928107702","https://openalex.org/W2962833140","https://openalex.org/W3092456670","https://openalex.org/W3104120816","https://openalex.org/W4288335707","https://openalex.org/W4321276751","https://openalex.org/W2948036864","https://openalex.org/W3034838723","https://openalex.org/W3213868621"],"abstract_inverted_index":{"Commonsense":[0],"reasoning":[1,21,43,61,77,102,110],"is":[2,37,90],"an":[3],"essential":[4],"and":[5],"vital":[6],"ability":[7,22,62,111],"for":[8,41,73],"humans":[9],"in":[10],"daily":[11],"life.":[12],"The":[13,120],"current":[14],"benchmark":[15,40],"fails":[16],"to":[17,58,68,99,106],"reflect":[18],"the":[19,24,60,64,69,82,91,95,101,108,117,128],"actual":[20],"of":[23,104,112,130],"language":[25,66,71,114,132],"model":[26,67,72],"equipped,":[27],"even":[28],"though":[29],"many":[30],"prior":[31],"works":[32],"received":[33],"impressive":[34],"performance.":[35],"DISCOSENSE":[36],"a":[38,55],"challenging":[39],"commonsense":[42,76,109],"via":[44],"understanding":[45],"various":[46],"discourse":[47,84],"connectives.":[48],"In":[49],"this":[50,75,89],"study,":[51],"we":[52],"manually":[53],"tailored":[54],"prompt":[56],"template":[57],"distill":[59,100],"from":[63],"large":[65],"small":[70,113,131],"conducting":[74],"task":[78],"by":[79],"explicitly":[80],"eliciting":[81],"multi-step":[83],"relation.":[85],"To":[86],"our":[87,124],"knowledge,":[88],"first":[92],"work":[93],"utilizing":[94],"knowledge":[96],"distillation":[97],"method":[98],"abilities":[103],"LLM":[105],"enhance":[107],"models":[115],"on":[116],"Discosense":[118],"task.":[119],"performance":[121],"demonstrates":[122],"that":[123],"approach":[125],"significantly":[126],"enhances":[127],"proficiency":[129],"models.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}