{"id":"https://openalex.org/W4411112900","doi":"https://doi.org/10.18653/v1/2025.findings-naacl.69","title":"Self-Training Large Language Models for Tool-Use Without Demonstrations","display_name":"Self-Training Large Language Models for Tool-Use Without Demonstrations","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411112900","doi":"https://doi.org/10.18653/v1/2025.findings-naacl.69"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-naacl.69","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-naacl.69","pdf_url":"https://aclanthology.org/2025.findings-naacl.69.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: NAACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-naacl.69.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068116015","display_name":"Nuan Luo","orcid":"https://orcid.org/0000-0002-8053-7750"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ne Luo","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080213009","display_name":"Aryo Pradipta Gema","orcid":"https://orcid.org/0009-0007-1163-3531"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Aryo Pradipta Gema","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060320196","display_name":"Xuanli He","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xuanli He","raw_affiliation_strings":["University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037724713","display_name":"Emile van Krieken","orcid":"https://orcid.org/0000-0001-5502-4817"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emile Van Krieken","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116235768","display_name":"Pietro Lesci","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pietro Lesci","raw_affiliation_strings":["University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019106673","display_name":"Pasquale Minervini","orcid":"https://orcid.org/0000-0002-8442-602X"},"institutions":[{"id":"https://openalex.org/I346547768","display_name":"Aims Community College","ror":"https://ror.org/01g325629","country_code":"US","type":"education","lineage":["https://openalex.org/I346547768"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Pasquale Minervini","raw_affiliation_strings":["Miniml.AI","University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Miniml.AI","institution_ids":["https://openalex.org/I346547768"]},{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.07845233,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1253","last_page":"1271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9642000198364258,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9642000198364258,"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/T10028","display_name":"Topic Modeling","score":0.9556999802589417,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9190000295639038,"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":0.812994658946991},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5902456045150757},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4943583011627197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3876468539237976},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3625602722167969},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.34560269117355347},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3253863453865051}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.812994658946991},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5902456045150757},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4943583011627197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3876468539237976},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3625602722167969},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.34560269117355347},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3253863453865051},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-naacl.69","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-naacl.69","pdf_url":"https://aclanthology.org/2025.findings-naacl.69.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: NAACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-naacl.69","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-naacl.69","pdf_url":"https://aclanthology.org/2025.findings-naacl.69.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: NAACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3186036607","display_name":null,"funder_award_id":"EP/S02431X/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"},{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"HORIZON2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"},{"id":"https://openalex.org/F4320307894","display_name":"Accenture","ror":"https://ror.org/013g16z83"},{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411112900.pdf","grobid_xml":"https://content.openalex.org/works/W4411112900.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2996078371"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"remain":[4],"prone":[5],"to":[6,24,43,53,64,117],"factual":[7],"inaccuracies":[8],"and":[9,14,75,94,126,132],"computational":[10],"errors,":[11],"including":[12],"hallucinations":[13],"mistakes":[15],"in":[16,56],"mathematical":[17],"reasoning.Recent":[18],"work":[19],"augmented":[20],"LLMs":[21,40,55,139],"with":[22],"tools":[23,45,137],"mitigate":[25],"these":[26],"shortcomings,":[27],"but":[28,115],"often":[29],"requires":[30],"curated":[31],"gold":[32],"tooluse":[33],"demonstrations.In":[34],"this":[35],"paper,":[36],"we":[37,48,59],"investigate":[38],"whether":[39],"can":[41],"learn":[42],"use":[44],"without":[46,140],"demonstrations.First,":[47],"analyse":[49],"zeroshot":[50],"prompting":[51],"strategies":[52],"guide":[54],"tool":[57],"utilisation.Second,":[58],"propose":[60],"a":[61,102],"self-training":[62],"method":[63],"synthesise":[65],"tool-use":[66,98],"traces":[67],"using":[68,86],"the":[69,81,130],"LLM":[70],"itself.We":[71],"compare":[72],"supervised":[73],"fine-tuning":[74,77],"preference":[76],"techniques":[78],"for":[79,113],"finetuning":[80],"model":[82],"on":[83,101,107,120],"datasets":[84],"constructed":[85],"existing":[87],"Question":[88],"Answering":[89],"(QA)":[90],"datasets,":[91,122],"i.e.,":[92,123],"TriviaQA":[93],"GSM8K.Experiments":[95],"show":[96],"that":[97],"enhances":[99],"performance":[100],"longtail":[103],"knowledge":[104],"task:":[105],"3.7%":[106],"PopQA,":[108],"which":[109],"is":[110],"used":[111],"solely":[112],"evaluation,":[114],"leads":[116],"mixed":[118],"results":[119],"other":[121],"TriviaQA,":[124],"GSM8K,":[125],"NQ-Open.Our":[127],"findings":[128],"highlight":[129],"potential":[131],"challenges":[133],"of":[134],"integrating":[135],"external":[136],"into":[138],"demonstrations.":[141]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}