{"id":"https://openalex.org/W4408356125","doi":"https://doi.org/10.1109/icassp49660.2025.10889153","title":"WTU-EVAL: A Whether-or-Not Tool Usage Evaluation Benchmark for Large Language Models","display_name":"WTU-EVAL: A Whether-or-Not Tool Usage Evaluation Benchmark for Large Language Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408356125","doi":"https://doi.org/10.1109/icassp49660.2025.10889153"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101745046","display_name":"Jian Liu","orcid":"https://orcid.org/0000-0002-4728-5678"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jian Liu","raw_affiliation_strings":["University of Science and Technology,Beijing"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology,Beijing","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031587216","display_name":"Ning Kang","orcid":"https://orcid.org/0000-0002-7317-8665"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kangyun Ning","raw_affiliation_strings":["Beijing Jiaotong University,Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102076759","display_name":"Yisong Su","orcid":null},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yisong Su","raw_affiliation_strings":["Fuzhou University,College of Computer and Data Science,Fuzhou,China"],"affiliations":[{"raw_affiliation_string":"Fuzhou University,College of Computer and Data Science,Fuzhou,China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101808738","display_name":"Wenjuan Han","orcid":"https://orcid.org/0000-0002-2327-0842"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjuan Han","raw_affiliation_strings":["Beijing Jiaotong University,Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101698034","display_name":"Jinan Xu","orcid":"https://orcid.org/0000-0003-0170-626X"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinan Xu","raw_affiliation_strings":["Beijing Jiaotong University,Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102811282","display_name":"Yuanzhe Zhang","orcid":"https://orcid.org/0000-0001-9905-9501"},"institutions":[{"id":"https://openalex.org/I4210148850","display_name":"National Science Library","ror":"https://ror.org/04ndjyr10","country_code":"CN","type":"archive","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210148850"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanzhe Zhang","raw_affiliation_strings":["Chinese Academy of Sciences,National Science Library,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,National Science Library,Beijing,China","institution_ids":["https://openalex.org/I4210148850"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101745046"],"corresponding_institution_ids":["https://openalex.org/I92403157"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02097977,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9725000262260437,"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":0.9725000262260437,"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":0.9713000059127808,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7851110696792603},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7649247050285339},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5065435171127319},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5049510598182678},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06162509322166443},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.04897356033325195}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7851110696792603},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7649247050285339},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5065435171127319},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5049510598182678},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06162509322166443},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.04897356033325195}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2130158090","https://openalex.org/W2606964149","https://openalex.org/W2889787757","https://openalex.org/W2946609015","https://openalex.org/W2998617917","https://openalex.org/W3034643750","https://openalex.org/W3035497479","https://openalex.org/W4389520103","https://openalex.org/W4389524004","https://openalex.org/W4404594861","https://openalex.org/W6762592649","https://openalex.org/W6764401283","https://openalex.org/W6803096969","https://openalex.org/W6840896190","https://openalex.org/W6846254642","https://openalex.org/W6848283410","https://openalex.org/W6849732303","https://openalex.org/W6850982024","https://openalex.org/W6852792400","https://openalex.org/W6853453387","https://openalex.org/W6853966477","https://openalex.org/W6854569510","https://openalex.org/W6854866820","https://openalex.org/W6855330075","https://openalex.org/W6856611373","https://openalex.org/W6856715111","https://openalex.org/W6857464309","https://openalex.org/W6857514456","https://openalex.org/W6858231316","https://openalex.org/W6860501820"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Although":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"excel":[5],"in":[6,129,135],"NLP":[7],"tasks,":[8],"they":[9],"still":[10],"need":[11],"external":[12],"tools":[13,42,51,73,108],"to":[14,62,85,106,110,125,144],"extend":[15],"their":[16,68,111,140],"ability.":[17],"Current":[18],"research":[19],"on":[20,118],"tool":[21,28,80,127],"learning":[22],"with":[23,35,88],"LLMs":[24,65,87,103,117,122],"often":[25],"assumes":[26],"mandatory":[27],"use,":[29],"which":[30],"does":[31],"not":[32],"always":[33],"align":[34],"real-world":[36],"situations,":[37],"where":[38,91],"the":[39,54,78],"necessity":[40],"for":[41],"is":[43,142],"uncertain,":[44],"and":[45,71,98,132],"incorrect":[46],"or":[47],"unnecessary":[48],"use":[49,72,107,128],"of":[50,57,93,115],"can":[52,66],"damage":[53],"general":[55,101,130],"abilities":[56],"LLMs.":[58],"Therefore,":[59],"we":[60],"propose":[61],"explore":[63],"whether":[64],"discern":[67],"ability":[69,141],"boundaries":[70],"flexibly.":[74],"We":[75],"then":[76],"introduce":[77],"Whether-or-not":[79],"usage":[81],"Evaluation":[82],"benchmark":[83],"(WTU-Eval)":[84],"assess":[86],"eleven":[89],"datasets,":[90,97,131],"six":[92],"them":[94],"are":[95,100,104],"tool-usage":[96,136],"five":[99],"datasets.":[102],"prompted":[105],"according":[109],"needs.":[112],"The":[113],"results":[114],"eight":[116],"WTU-Eval":[119],"reveal":[120],"that":[121],"frequently":[123],"struggle":[124],"determine":[126],"LLMs\u2019":[133],"performance":[134],"datasets":[137],"improves":[138],"when":[139],"similar":[143],"ChatGPT.":[145]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}