{"id":"https://openalex.org/W4416034428","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1229","title":"NUMINA: A Natural Understanding Benchmark for Multi-dimensional Intelligence and Numerical Reasoning Abilities","display_name":"NUMINA: A Natural Understanding Benchmark for Multi-dimensional Intelligence and Numerical Reasoning Abilities","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034428","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1229"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1229","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1229","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1229.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1229.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048713515","display_name":"Changyu Zeng","orcid":"https://orcid.org/0000-0002-3756-8463"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changyu Zeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yifan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103119465","display_name":"Zimu Wang","orcid":"https://orcid.org/0009-0008-4332-5514"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zimu Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391855","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-0707-8076"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023716533","display_name":"Zhengni Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengni Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101805094","display_name":"Muyi Bao","orcid":"https://orcid.org/0009-0001-5615-8638"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Muyi Bao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011918180","display_name":"Jimin Xiao","orcid":"https://orcid.org/0000-0002-9416-2486"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jimin Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027524719","display_name":"Kim-Anh Nguyen","orcid":"https://orcid.org/0000-0002-1000-3112"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anh Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5052861384","display_name":"Yutao Yue","orcid":"https://orcid.org/0000-0003-4532-0924"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yutao Yue","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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22575","last_page":"22590"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.12290000170469284,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.12290000170469284,"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/T10130","display_name":"Mathematics Education and Teaching Techniques","score":0.10570000112056732,"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"}},{"id":"https://openalex.org/T10533","display_name":"Teaching and Learning Programming","score":0.08619999885559082,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.49540001153945923},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4602000117301941},{"id":"https://openalex.org/keywords/qualitative-reasoning","display_name":"Qualitative reasoning","score":0.35370001196861267},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.3495999872684479},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.296099990606308},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.2703999876976013}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6021999716758728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.548799991607666},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.49540001153945923},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4602000117301941},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.3495999872684479},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28450000286102295},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.25220000743865967},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1229","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1229","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1229.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.1229","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1229","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1229.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/W4416034428.pdf","grobid_xml":"https://content.openalex.org/works/W4416034428.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1,138],"in":[2,13,123,139],"2D":[3],"multimodal":[4,75,119],"large":[5],"language":[6],"models":[7],"(MLLMs)":[8],"have":[9],"significantly":[10],"improved":[11],"performance":[12,102],"vision-language":[14],"tasks.However,":[15],"extending":[16],"these":[17],"capabilities":[18],"to":[19,27,46,73],"3D":[20,34,140],"environments":[21],"remains":[22],"a":[23],"distinct":[24],"challenge":[25],"due":[26],"the":[28,61,101,110,134],"complexity":[29],"of":[30,103],"spatial":[31,49],"reasoning.Nevertheless,":[32],"existing":[33],"benchmarks":[35],"often":[36],"lack":[37],"fine-grained":[38],"numerical":[39,53,120],"reasoning":[40,71],"task":[41],"annotations,":[42],"limiting":[43],"MLLMs'":[44],"ability":[45],"perform":[47],"precise":[48,125],"measurements":[50],"and":[51,69,82,97,130,143],"complex":[52],"reasoning.To":[54],"address":[55],"this":[56],"gap,":[57],"we":[58],"introduce":[59],"NUMINA,":[60],"first":[62],"Natural":[63],"Understanding":[64],"benchmark":[65],"for":[66,136],"Multi-dimensional":[67],"Intelligence":[68],"Numerical":[70],"Abilities":[72],"enhance":[74],"indoor":[76],"perceptual":[77],"understanding.NUMINA":[78],"features":[79],"multi-scale":[80],"annotations":[81],"various":[83,104],"question-answer":[84],"pairs,":[85],"generated":[86],"using":[87],"NUMINA-Flow,":[88],"an":[89],"automated":[90],"annotation":[91],"pipeline":[92],"that":[93,114],"integrates":[94],"LLM":[95],"rewriting":[96],"rule-based":[98],"self-verification.We":[99],"evaluate":[100],"state-of-the-art":[105],"LLMs":[106,116],"on":[107],"NUMINA":[108],"following":[109],"Chat-Scene":[111],"framework,":[112],"demonstrating":[113],"current":[115],"struggle":[117],"with":[118],"reasoning,":[121],"particularly":[122],"performing":[124],"computations":[126],"such":[127],"as":[128],"distance":[129],"volume":[131],"estimation,":[132],"highlighting":[133],"need":[135],"further":[137],"models.The":[141],"dataset":[142],"source":[144],"codes":[145],"can":[146],"be":[147],"obtained":[148],"from":[149],"https://github.com/":[150],"fengshun124/NUMINA.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}