{"id":"https://openalex.org/W4392902994","doi":"https://doi.org/10.1109/icassp48485.2024.10446355","title":"Can LLM Find the Green Circle? Investigation and Human-Guided Tool Manipulation for Compositional Generalization","display_name":"Can LLM Find the Green Circle? Investigation and Human-Guided Tool Manipulation for Compositional Generalization","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902994","doi":"https://doi.org/10.1109/icassp48485.2024.10446355"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446355","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5102893256","display_name":"Min Zhang","orcid":"https://orcid.org/0009-0003-8280-7886"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Virginia Tech,Department of Computer Science,Falls Church,VA,USA","Department of Computer Science, Virginia Tech, Falls Church, VA, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Tech,Department of Computer Science,Falls Church,VA,USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Falls Church, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103096924","display_name":"Jianfeng He","orcid":"https://orcid.org/0000-0002-7700-788X"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianfeng He","raw_affiliation_strings":["Virginia Tech,Department of Computer Science,Falls Church,VA,USA","Department of Computer Science, Virginia Tech, Falls Church, VA, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Tech,Department of Computer Science,Falls Church,VA,USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Falls Church, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034757629","display_name":"Shuo Lei","orcid":"https://orcid.org/0000-0001-7031-2438"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuo Lei","raw_affiliation_strings":["Virginia Tech,Department of Computer Science,Falls Church,VA,USA","Department of Computer Science, Virginia Tech, Falls Church, VA, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Tech,Department of Computer Science,Falls Church,VA,USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Falls Church, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101232646","display_name":"Murong Yue","orcid":null},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Murong Yue","raw_affiliation_strings":["George Mason University,Department of Computer Science,Fairfax,VA,USA","Department of Computer Science, George Mason University, Fairfax, VA, USA"],"affiliations":[{"raw_affiliation_string":"George Mason University,Department of Computer Science,Fairfax,VA,USA","institution_ids":["https://openalex.org/I162714631"]},{"raw_affiliation_string":"Department of Computer Science, George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063375262","display_name":"Linhan Wang","orcid":"https://orcid.org/0009-0000-8057-1767"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linhan Wang","raw_affiliation_strings":["Virginia Tech,Department of Computer Science,Falls Church,VA,USA","Department of Computer Science, Virginia Tech, Falls Church, VA, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Tech,Department of Computer Science,Falls Church,VA,USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Falls Church, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038002204","display_name":"Chang\u2010Tien Lu","orcid":"https://orcid.org/0000-0003-3675-0199"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chang-Tien Lu","raw_affiliation_strings":["Virginia Tech,Department of Computer Science,Falls Church,VA,USA","Department of Computer Science, Virginia Tech, Falls Church, VA, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Tech,Department of Computer Science,Falls Church,VA,USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Falls Church, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102893256"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61690083,"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":"11996","last_page":"12000"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/generalization","display_name":"Generalization","score":0.914928138256073},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7761547565460205},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.666147768497467},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6341593265533447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5904070138931274},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4527183473110199},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.44321465492248535},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3987555503845215},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09602117538452148},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08858859539031982},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07199165225028992}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.914928138256073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7761547565460205},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.666147768497467},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6341593265533447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5904070138931274},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4527183473110199},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.44321465492248535},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3987555503845215},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09602117538452148},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08858859539031982},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07199165225028992},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446355","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2107019937","https://openalex.org/W3104739822","https://openalex.org/W3105725479","https://openalex.org/W3116829624","https://openalex.org/W3177023643","https://openalex.org/W3203966499","https://openalex.org/W4221143046","https://openalex.org/W4281557260","https://openalex.org/W4292779060","https://openalex.org/W4309953112","https://openalex.org/W4362515116","https://openalex.org/W4378718568","https://openalex.org/W4385573248","https://openalex.org/W4386065691","https://openalex.org/W4389523957","https://openalex.org/W6748655984","https://openalex.org/W6771829773","https://openalex.org/W6778883912","https://openalex.org/W6782125931","https://openalex.org/W6782501987","https://openalex.org/W6800487080","https://openalex.org/W6805736498","https://openalex.org/W6809646742","https://openalex.org/W6838865847","https://openalex.org/W6845478269","https://openalex.org/W6846874006","https://openalex.org/W6851775633","https://openalex.org/W6853064329"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W2080152487","https://openalex.org/W3083152911","https://openalex.org/W3022347918","https://openalex.org/W4200527723"],"abstract_inverted_index":{"The":[0,14],"meaning":[1],"of":[2,10,16,27,121],"complex":[3,81],"phrases":[4],"in":[5,72,88],"natural":[6],"language":[7,41],"is":[8],"composed":[9],"their":[11,55],"individual":[12],"components.":[13,28],"task":[15],"compositional":[17,58,73,82,140],"generalization":[18,46,59,141],"evaluates":[19],"a":[20,101],"model\u2019s":[21],"ability":[22],"to":[23,85],"understand":[24],"new":[25],"combinations":[26],"Previous":[29],"studies":[30],"trained":[31],"smaller,":[32],"task-specific":[33],"models,":[34],"which":[35],"exhibited":[36],"poor":[37],"generalization.":[38,74],"While":[39],"large":[40],"models":[42],"(LLMs)":[43],"exhibit":[44],"impressive":[45],"abilities":[47],"on":[48,138,147],"many":[49],"tasks":[50],"through":[51],"in-context":[52],"learning":[53],"(ICL),":[54],"potential":[56],"for":[57,96,110],"remains":[60],"unexplored.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65,99],"first":[66],"empirically":[67],"investigate":[68],"prevailing":[69],"ICL":[70],"methods":[71,146],"We":[75],"find":[76],"that":[77,107,132],"they":[78],"struggle":[79],"with":[80,126],"questions":[83],"due":[84],"cumulative":[86],"errors":[87],"long":[89],"reasoning":[90],"steps":[91],"and":[92,112,124,143],"intricate":[93],"logic":[94],"required":[95],"tool-making.":[97],"Consequently,":[98],"propose":[100],"human-guided":[102],"tool":[103,122],"manipulation":[104],"framework":[105],"(HTM)":[106],"generates":[108],"tools":[109],"sub-questions":[111],"integrates":[113],"multiple":[114],"tools.":[115],"Our":[116],"method":[117,134],"enhances":[118],"the":[119,148],"effectiveness":[120],"creation":[123],"usage":[125],"minimal":[127],"human":[128],"effort.":[129],"Experiments":[130],"show":[131],"our":[133],"achieves":[135],"state-of-the-art":[136],"performance":[137],"two":[139],"benchmarks":[142],"outperforms":[144],"existing":[145],"most":[149],"challenging":[150],"test":[151],"split":[152],"by":[153],"nearly":[154],"70%.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}