{"id":"https://openalex.org/W4415536793","doi":"https://doi.org/10.1145/3746027.3754571","title":"Enhancing the Geometric Problem-Solving Ability of Multimodal LLMs via Symbolic-Neural Integration","display_name":"Enhancing the Geometric Problem-Solving Ability of Multimodal LLMs via Symbolic-Neural Integration","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536793","doi":"https://doi.org/10.1145/3746027.3754571"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754571","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107677635","display_name":"Yicheng Pan","orcid":"https://orcid.org/0009-0005-0233-2417"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yicheng Pan","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0005-0233-2417","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039254301","display_name":"Zhenrong Zhang","orcid":"https://orcid.org/0000-0001-9211-0749"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenrong Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-9211-0749","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101623000","display_name":"Pengfei Hu","orcid":"https://orcid.org/0009-0005-3345-605X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Hu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0005-3345-605X","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006572116","display_name":"Jiefeng Ma","orcid":"https://orcid.org/0000-0003-2416-3720"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiefeng Ma","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-2416-3720","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-2387-0389","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101760682","display_name":"Jianshu Zhang","orcid":"https://orcid.org/0000-0002-2713-2535"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianshu Zhang","raw_affiliation_strings":["iFLYTEK Research, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-2713-2535","affiliations":[{"raw_affiliation_string":"iFLYTEK Research, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115596605","display_name":"Quan Liu","orcid":"https://orcid.org/0009-0007-1116-9046"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quan Liu","raw_affiliation_strings":["iFLYTEK Research, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0007-1116-9046","affiliations":[{"raw_affiliation_string":"iFLYTEK Research, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020540834","display_name":"Jianqing Gao","orcid":"https://orcid.org/0000-0001-5575-4940"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianqing Gao","raw_affiliation_strings":["iFLYTEK Research, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5575-4940","affiliations":[{"raw_affiliation_string":"iFLYTEK Research, Hefei, China","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Feng Ma","orcid":"https://orcid.org/0009-0009-4837-8276"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng Ma","raw_affiliation_strings":["iFLYTEK Research, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0009-4837-8276","affiliations":[{"raw_affiliation_string":"iFLYTEK Research, Hefei, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5394","last_page":"5403"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9708999991416931,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.953499972820282,"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/process","display_name":"Process (computing)","score":0.5501999855041504},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.5313000082969666},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.5037000179290771},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4952000081539154},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.46050000190734863},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.4602000117301941},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.36910000443458557},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.3571999967098236}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6653000116348267},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5501999855041504},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5313000082969666},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.5037000179290771},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4952000081539154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46639999747276306},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46050000190734863},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.4602000117301941},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3571999967098236},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C2776095079","wikidata":"https://www.wikidata.org/wiki/Q489538","display_name":"The Symbolic","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C21847791","wikidata":"https://www.wikidata.org/wiki/Q191081","display_name":"Logical conjunction","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C60229501","wikidata":"https://www.wikidata.org/wiki/Q18822","display_name":"Global Positioning System","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29760000109672546},{"id":"https://openalex.org/C203702819","wikidata":"https://www.wikidata.org/wiki/Q17146953","display_name":"Logical data model","level":3,"score":0.27950000762939453},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754571","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W3176186248","https://openalex.org/W3176371077","https://openalex.org/W4225105060","https://openalex.org/W4385572160","https://openalex.org/W4385572852","https://openalex.org/W4385768252","https://openalex.org/W4389520727","https://openalex.org/W4390048370","https://openalex.org/W4390940921","https://openalex.org/W4401834466","https://openalex.org/W4402670709","https://openalex.org/W4404781880","https://openalex.org/W4404783478"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,12,18],"Multimodal":[3],"Large":[4,88],"Language":[5,89],"Models":[6],"(MLLMs)":[7],"have":[8],"achieved":[9],"remarkable":[10,139],"progress":[11],"general":[13],"domains":[14],"and":[15,40,105,123,158,166],"demonstrated":[16],"promise":[17],"multimodal":[19],"mathematical":[20],"reasoning.":[21,44],"However,":[22],"applying":[23],"MLLMs":[24],"to":[25,33,112],"geometry":[26,61],"problem":[27],"solving":[28],"(GPS)":[29],"remains":[30],"challenging":[31],"due":[32],"lack":[34],"of":[35,82,136,153,156],"accurate":[36],"step-by-step":[37],"solution":[38],"data":[39,94],"severe":[41],"hallucinations":[42],"during":[43],"In":[45],"this":[46],"paper,":[47],"we":[48,84],"propose":[49],"GeoGen,":[50],"a":[51,87,100,163],"pipeline":[52],"that":[53,129],"can":[54],"automatically":[55],"generates":[56],"step-wise":[57],"reasoning":[58,80,119,145],"paths":[59],"for":[60,143,169],"diagrams.":[62],"By":[63],"leveraging":[64],"the":[65,78,118,134,154,170],"precise":[66],"symbolic":[67,106,110,159],"reasoning,":[68],"GeoGen":[69],"produces":[70],"large-scale,":[71],"high-quality":[72],"question-answer":[73],"pairs.":[74],"To":[75],"further":[76],"enhance":[77],"logical":[79],"ability":[81],"MLLMs,":[83,137],"train":[85],"GeoLogic,":[86],"Model":[90],"(LLM)":[91],"using":[92],"synthetic":[93],"generated":[95],"by":[96],"GeoGen.":[97],"Serving":[98],"as":[99],"bridge":[101],"between":[102],"natural":[103],"language":[104],"systems,":[107,160],"GeoLogic":[108],"enables":[109,162],"tools":[111],"help":[113],"verifying":[114],"MLLM":[115],"outputs,":[116],"making":[117],"process":[120],"more":[121,164],"rigorous":[122],"alleviating":[124],"hallucinations.":[125],"Experimental":[126],"results":[127,140],"show":[128],"our":[130,151],"approach":[131,168],"consistently":[132],"improves":[133],"performance":[135],"achieving":[138],"on":[141],"benchmarks":[142],"geometric":[144],"tasks.":[146],"This":[147],"improvement":[148],"stems":[149],"from":[150],"integration":[152],"strengths":[155],"LLMs":[157],"which":[161],"reliable":[165],"interpretable":[167],"GPS":[171],"task.":[172],"Codes":[173],"are":[174],"available":[175],"at":[176],"https://github.com/ycpNotFound/GeoGen.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}