{"id":"https://openalex.org/W4412888373","doi":"https://doi.org/10.18653/v1/2025.findings-acl.610","title":"Physics: Benchmarking Foundation Models on University-Level Physics Problem Solving","display_name":"Physics: Benchmarking Foundation Models on University-Level Physics Problem Solving","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888373","doi":"https://doi.org/10.18653/v1/2025.findings-acl.610"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.610","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.610","pdf_url":"https://aclanthology.org/2025.findings-acl.610.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.610.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kaiyue Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaiyue Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047416722","display_name":"Yilun Zhao","orcid":"https://orcid.org/0000-0002-6812-5120"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yilun Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386682","display_name":"Yixin Liu","orcid":"https://orcid.org/0000-0002-4309-5076"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixin Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061389668","display_name":"Tianyu Yang","orcid":"https://orcid.org/0000-0002-6328-8932"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyu Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352014","display_name":"Chen Zhao","orcid":"https://orcid.org/0000-0003-2167-2490"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012867203","display_name":"John Sous","orcid":"https://orcid.org/0000-0002-9994-5789"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John Sous","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5064858748","display_name":"Arman Cohan","orcid":"https://orcid.org/0000-0002-8954-2724"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arman Cohan","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10342375,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11717","last_page":"11743"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11715","display_name":"Education and Critical Thinking Development","score":0.8453999757766724,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11715","display_name":"Education and Critical Thinking Development","score":0.8453999757766724,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8311663269996643},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.6947797536849976},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.6136062741279602},{"id":"https://openalex.org/keywords/engineering-physics","display_name":"Engineering physics","score":0.3944729268550873},{"id":"https://openalex.org/keywords/management","display_name":"Management","score":0.0844317078590393}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8311663269996643},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6947797536849976},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.6136062741279602},{"id":"https://openalex.org/C61696701","wikidata":"https://www.wikidata.org/wiki/Q770766","display_name":"Engineering physics","level":1,"score":0.3944729268550873},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0844317078590393},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.610","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.610","pdf_url":"https://aclanthology.org/2025.findings-acl.610.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.610","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.610","pdf_url":"https://aclanthology.org/2025.findings-acl.610.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/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888373.pdf","grobid_xml":"https://content.openalex.org/works/W4412888373.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W4238897586","https://openalex.org/W2935759653","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W3105167352","https://openalex.org/W54078636","https://openalex.org/W2284465472"],"abstract_inverted_index":{"We":[0],"introduce":[1],"PHYSICS,":[2],"a":[3,41],"comprehensive":[4,76],"benchmark":[5],"for":[6,46,94,99],"university-level":[7],"physics":[8,35],"problem":[9,32],"solving.It":[10],"contains":[11],"1,297":[12],"expert-annotated":[13],"problems":[14],"covering":[15],"six":[16],"core":[17],"areas:":[18],"classical":[19],"mechanics,":[20,22,26],"quantum":[21],"thermodynamics":[23],"and":[24,30,37,48,84],"statistical":[25],"electromagnetism,":[27],"atomic":[28],"physics,":[29],"optics.Each":[31],"requires":[33],"advanced":[34,61],"knowledge":[36,88],"mathematical":[38],"reasoning.We":[39],"develop":[40],"robust":[42],"automated":[43],"evaluation":[44,51],"system":[45],"precise":[47],"reliable":[49],"validation.Our":[50],"of":[52,80],"leading":[53],"foundation":[54,98],"models":[55],"reveals":[56],"substantial":[57],"limitations.Even":[58],"the":[59,97],"most":[60],"model,":[62],"o3-mini,":[63],"achieves":[64],"only":[65],"59.9%":[66],"accuracy,":[67],"highlighting":[68],"significant":[69],"challenges":[70],"in":[71],"solving":[72],"high-level":[73],"scientific":[74],"problems.Through":[75],"error":[77],"analysis,":[78],"exploration":[79],"diverse":[81],"prompting":[82],"strategies,":[83],"Retrieval-Augmented":[85],"Generation":[86],"(RAG)-based":[87],"augmentation,":[89],"we":[90],"identify":[91],"key":[92],"areas":[93],"improvement,":[95],"laying":[96],"future":[100],"advancements.":[101]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
