{"id":"https://openalex.org/W4412887680","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1172","title":"Evaluating LLMs\u2019 Mathematical and Coding Competency through Ontology-guided Interventions","display_name":"Evaluating LLMs\u2019 Mathematical and Coding Competency through Ontology-guided Interventions","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887680","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1172"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1172","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1172","pdf_url":"https://aclanthology.org/2025.findings-acl.1172.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: ACL 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-acl.1172.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100549161","display_name":"Pengfei Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengfei Hong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007003459","display_name":"Navonil Majumder","orcid":"https://orcid.org/0000-0002-1449-617X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Navonil Majumder","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086877005","display_name":"Deepanway Ghosal","orcid":"https://orcid.org/0000-0002-3858-4449"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deepanway Ghosal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071844229","display_name":"Somak Aditya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Somak Aditya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082450455","display_name":"Rada Mihalcea","orcid":"https://orcid.org/0000-0002-0767-6703"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rada Mihalcea","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033376109","display_name":"Soujanya Poria","orcid":"https://orcid.org/0000-0001-6924-7931"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soujanya Poria","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22811","last_page":"22849"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12171","display_name":"Open Education and E-Learning","score":0.9811999797821045,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T12171","display_name":"Open Education and E-Learning","score":0.9811999797821045,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9684000015258789,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/ontology","display_name":"Ontology","score":0.6662722826004028},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.589372992515564},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5865306854248047},{"id":"https://openalex.org/keywords/psychological-intervention","display_name":"Psychological intervention","score":0.5788494944572449},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.3372003436088562},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.16632258892059326},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.0886116623878479},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.08341234922409058},{"id":"https://openalex.org/keywords/social-science","display_name":"Social science","score":0.08332830667495728},{"id":"https://openalex.org/keywords/nursing","display_name":"Nursing","score":0.07408922910690308}],"concepts":[{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.6662722826004028},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.589372992515564},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5865306854248047},{"id":"https://openalex.org/C27415008","wikidata":"https://www.wikidata.org/wiki/Q7256382","display_name":"Psychological intervention","level":2,"score":0.5788494944572449},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3372003436088562},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.16632258892059326},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0886116623878479},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.08341234922409058},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.08332830667495728},{"id":"https://openalex.org/C159110408","wikidata":"https://www.wikidata.org/wiki/Q121176","display_name":"Nursing","level":1,"score":0.07408922910690308},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1172","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1172","pdf_url":"https://aclanthology.org/2025.findings-acl.1172.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: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1172","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1172","pdf_url":"https://aclanthology.org/2025.findings-acl.1172.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: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887680.pdf","grobid_xml":"https://content.openalex.org/works/W4412887680.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,31,40,94,136],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"have":[7],"showcased":[8],"striking":[9],"results":[10],"on":[11,45],"existing":[12],"logical":[13],"reasoning":[14,32,48,51,96,134],"benchmarks,":[15],"with":[16],"some":[17],"models":[18,117],"even":[19],"surpassing":[20],"human":[21],"performance.However,":[22],"the":[23,116,119,124,145],"true":[24],"depth":[25],"of":[26,61,84,102],"their":[27],"competencies":[28],"and":[29,52,65,76,81,87,97,105,132,147],"robustness":[30],"tasks":[33],"remains":[34],"an":[35],"open":[36],"question.To":[37],"this":[38,41],"end,":[39],"paper,":[42],"we":[43,55,108],"focus":[44],"two":[46,78],"popular":[47],"tasks:":[49],"arithmetic":[50],"code":[53,149],"generation.Particularly,":[54],"introduce":[56],"(i)":[57],"a":[58,69,110],"general":[59],"ontology":[60],"perturbations":[62],"for":[63],"math":[64,86],"coding":[66,88,98],"questions,":[67,121],"(ii)":[68],"semi-automatic":[70],"method":[71],"to":[72,90],"apply":[73],"these":[74],"perturbations,":[75],"(iii)":[77],"datasets,":[79],"GSMORE":[80],"HUMANEVAL-CORE,":[82],"respectively,":[83],"perturbed":[85,120],"problems":[89],"probe":[91],"LLM":[92],"capabilities":[93],"numeric":[95],"tasks.Through":[99],"comprehensive":[100],"evaluations":[101],"both":[103],"closed-source":[104],"opensource":[106],"LLMs,":[107],"show":[109],"significant":[111],"performance":[112],"drop":[113],"across":[114],"all":[115],"against":[118],"suggesting":[122],"that":[123],"current":[125],"LLMs":[126],"lack":[127],"robust":[128],"problem":[129],"solving":[130],"skills":[131],"structured":[133],"abilities":[135],"many":[137],"areas,":[138],"as":[139],"defined":[140],"by":[141],"our":[142],"ontology.We":[143],"open-source":[144],"datasets":[146],"source":[148],"at:":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
