{"id":"https://openalex.org/W4416034096","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1196","title":"Benchmarking Foundation Models with Retrieval-Augmented Generation in Olympic-Level Physics Problem Solving","display_name":"Benchmarking Foundation Models with Retrieval-Augmented Generation in Olympic-Level Physics Problem Solving","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034096","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1196"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1196","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1196","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1196.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1196.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shunfeng Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shunfeng Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100725640","display_name":"Yudi Zhang","orcid":"https://orcid.org/0000-0002-7830-5133"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yudi Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400486","display_name":"Meng Fang","orcid":"https://orcid.org/0000-0001-6745-286X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng Fang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410563","display_name":"Zihan Zhang","orcid":"https://orcid.org/0009-0004-8852-8156"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zihan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050193246","display_name":"Zhitan Wu","orcid":"https://orcid.org/0009-0002-6124-428X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhitan Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022601535","display_name":"Mykola Pechenizkiy","orcid":"https://orcid.org/0000-0003-4955-0743"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mykola Pechenizkiy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100411139","display_name":"Ling Chen","orcid":"https://orcid.org/0000-0003-1934-5992"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ling Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"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":0.34272654,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21927","last_page":"21956"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.188400000333786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.188400000333786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.09040000289678574,"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"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.03620000183582306,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.566100001335144},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.5134000182151794},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.3610999882221222},{"id":"https://openalex.org/keywords/mathematical-model","display_name":"Mathematical model","score":0.2651999890804291}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.566100001335144},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5134000182151794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4787999987602234},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3790000081062317},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.35359999537467957},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.35339999198913574},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.29010000824928284},{"id":"https://openalex.org/C76969082","wikidata":"https://www.wikidata.org/wiki/Q486902","display_name":"Mathematical model","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.23680000007152557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1196","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1196","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1196.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1196","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1196","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1196.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034096.pdf","grobid_xml":"https://content.openalex.org/works/W4416034096.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1],"(RAG)":[2],"with":[3,98,106],"foundation":[4,48,85],"models":[5,91,96],"has":[6],"achieved":[7],"strong":[8],"performance":[9],"across":[10],"diverse":[11],"tasks,":[12],"but":[13],"their":[14],"capacity":[15],"for":[16,31,58],"expert-level":[17],"reasoning-such":[18],"as":[19],"solving":[20],"Olympiad-level":[21,59],"physics":[22,45,78,107,123],"problems-remains":[23],"largely":[24],"unexplored.Inspired":[25],"by":[26,33],"the":[27,39,73],"way":[28],"students":[29],"prepare":[30],"competitions":[32],"reviewing":[34],"past":[35],"problems,":[36],"we":[37,82],"investigate":[38],"potential":[40],"of":[41,64,77],"RAG":[42],"to":[43],"enhance":[44],"reasoning":[46],"in":[47,121],"models.We":[49],"introduce":[50],"PhoPile,":[51,81],"a":[52],"high-quality":[53],"multimodal":[54,75,95],"dataset":[55],"specifically":[56],"designed":[57],"physics,":[60],"enabling":[61],"systematic":[62],"study":[63],"retrieval-based":[65],"reasoning.PhoPile":[66],"includes":[67],"diagrams,":[68],"graphs,":[69],"and":[70,93],"equations,":[71],"capturing":[72],"inherently":[74],"nature":[76],"problem":[79],"solving.Using":[80],"benchmark":[83],"RAG-augmented":[84],"models,":[86],"covering":[87],"both":[88],"large":[89,94],"language":[90],"(LLMs)":[92],"(LMMs)":[97],"multiple":[99],"retrievers.Our":[100],"results":[101],"demonstrate":[102],"that":[103,117],"integrating":[104],"retrieval":[105],"corpora":[108],"can":[109],"improve":[110],"model":[111],"performance,":[112],"while":[113],"also":[114],"highlighting":[115],"challenges":[116],"motivate":[118],"further":[119],"research":[120],"retrieval-augmented":[122],"reasoning.":[124]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}