{"id":"https://openalex.org/W7126441971","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.22","title":"A Comprehensive Evaluation of Inductive Reasoning Capabilities and Problem Solving in Large Language Models","display_name":"A Comprehensive Evaluation of Inductive Reasoning Capabilities and Problem Solving in Large Language Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126441971","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.22"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.22","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.22","pdf_url":"https://aclanthology.org/2024.findings-eacl.22.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: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.22.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124516150","display_name":"Chen Bowen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Bowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124624673","display_name":"Rune S\u00e6tre","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rune S\u00e6tre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124544698","display_name":"Yusuke Miyao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yusuke Miyao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3055,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70268537,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"323","last_page":"339"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.15520000457763672,"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":0.15520000457763672,"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":0.0940999984741211,"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/T13629","display_name":"Text Readability and Simplification","score":0.07479999959468842,"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/automated-reasoning","display_name":"Automated reasoning","score":0.4546999931335449},{"id":"https://openalex.org/keywords/inductive-reasoning","display_name":"Inductive reasoning","score":0.4422999918460846},{"id":"https://openalex.org/keywords/non-monotonic-logic","display_name":"Non-monotonic logic","score":0.33219999074935913},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.3084999918937683},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3057999908924103},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.298799991607666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6284000277519226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49230000376701355},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.4546999931335449},{"id":"https://openalex.org/C21563000","wikidata":"https://www.wikidata.org/wiki/Q484511","display_name":"Inductive reasoning","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34299999475479126},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.298799991607666},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.22","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.22","pdf_url":"https://aclanthology.org/2024.findings-eacl.22.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: EACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.22","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.22","pdf_url":"https://aclanthology.org/2024.findings-eacl.22.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: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","score":0.5530100464820862,"display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126441971.pdf","grobid_xml":"https://content.openalex.org/works/W7126441971.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Inductive":[0],"reasoning":[1,11,38],"is":[2,31,39],"fundamental":[3],"to":[4,78,155],"both":[5],"human":[6],"and":[7,34,50,64],"artificial":[8],"intelligence.The":[9],"inductive":[10,37],"abilities":[12],"of":[13,29,60,76,103,110],"current":[14],"Large":[15],"Language":[16],"Models":[17],"(LLMs)":[18],"are":[19],"evaluated":[20],"in":[21,89,99,147],"this":[22],"research.We":[23],"argue":[24,121],"that":[25,66,86,122,141],"only":[26],"considering":[27],"induction":[28],"rules":[30,46],"too":[32],"narrow":[33],"unrealistic,":[35],"since":[36],"usually":[40],"mixed":[41],"with":[42,57],"other":[43],"abilities,":[44],"like":[45],"application,":[47],"results/rules":[48],"validation,":[49],"updated":[51],"information":[52],"integration.We":[53],"probed":[54],"the":[55,74,96,104,108,115,126,130,134,158,162],"LLMs":[56,70,77,127,135],"a":[58,90,100],"set":[59],"designed":[61],"symbolic":[62],"tasks":[63],"found":[65,85],"even":[67],"state-of-theart":[68],"(SotA)":[69],"fail":[71,156],"significantly,":[72],"showing":[73],"inability":[75],"perform":[79],"these":[80],"intuitively":[81],"simple":[82],"tasks.Furthermore,":[83],"we":[84,112,139],"perfect":[87],"accuracy":[88,98],"small-size":[91],"problem":[92,159],"does":[93],"not":[94],"guarantee":[95],"same":[97,105],"larger-size":[101],"version":[102],"problem,":[106],"provoking":[107],"question":[109],"how":[111],"can":[113],"assess":[114],"LLMs'":[116],"actual":[117],"problem-solving":[118,131],"capabilities.We":[119],"also":[120],"Chain-of-Thought":[123],"prompts":[124],"help":[125],"by":[128],"decomposing":[129],"process,":[132],"but":[133],"still":[136],"learn":[137],"limitedly.Furthermore,":[138],"reveal":[140],"few-shot":[142,164],"examples":[143],"assist":[144],"LLM":[145,153],"generalization":[146],"out-of-domain":[148],"(OOD)":[149],"cases,":[150],"albeit":[151],"limited.The":[152],"starts":[154],"when":[157],"deviates":[160],"from":[161],"provided":[163],"examples.":[165],"Raw":[166],"Observation":[167],"Results":[168,177,179],"Rule":[169,174],"Rules":[170,182],"ApplicationPossibly":[171],"Wrong":[172],"Result":[173,176],"Validated":[175],"ValidationCorrect":[178],"Possibly":[180],"Incorrect":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-02T00:00:00"}