{"id":"https://openalex.org/W4416034384","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1400","title":"GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning","display_name":"GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034384","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1400"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1400","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1400","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1400.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.1400.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101648428","display_name":"Guizhen Chen","orcid":"https://orcid.org/0009-0004-5270-2730"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guizhen Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038269510","display_name":"Weiwen Xu","orcid":"https://orcid.org/0000-0002-6090-2984"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiwen Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092393033","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0001-8043-9184"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101761759","display_name":"Hou Pong Chan","orcid":"https://orcid.org/0000-0001-9207-4178"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hou Pong Chan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102288415","display_name":"Deli Zhao","orcid":"https://orcid.org/0000-0001-6193-6361"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deli Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050386762","display_name":"Anh Tuan Luu","orcid":"https://orcid.org/0000-0002-1927-9895"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anh Tuan Luu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100767600","display_name":"Yu Rong","orcid":"https://orcid.org/0000-0001-7387-302X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Rong","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":1.9814,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88191813,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"25680","last_page":"25688"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.5002999901771545,"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":0.5002999901771545,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1597999930381775,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.04349999874830246,"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/bridging","display_name":"Bridging (networking)","score":0.7059000134468079},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5185999870300293},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.3621000051498413},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.34619998931884766},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3100000023841858}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7059000134468079},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5275999903678894},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5185999870300293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49239999055862427},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3882000148296356},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3621000051498413},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3240000009536743},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.28859999775886536},{"id":"https://openalex.org/C2983864324","wikidata":"https://www.wikidata.org/wiki/Q16872183","display_name":"Line drawings","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2653000056743622},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.26249998807907104}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1400","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1400","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1400.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.1400","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1400","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1400.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":[{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034384.pdf","grobid_xml":"https://content.openalex.org/works/W4416034384.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,25,44,76,145],"reinforcement":[3],"learning":[4],"(RL)":[5],"have":[6],"enhanced":[7],"the":[8,17,41,48,98,124,140],"reasoning":[9,51,106,115,126],"abilities":[10],"of":[11,50,74,101,142],"large":[12],"language":[13],"models":[14],"(LLMs),":[15],"yet":[16],"impact":[18],"on":[19,69],"multimodal":[20],"LLMs":[21],"(MLLMs)":[22],"is":[23],"limited.Particularly":[24],"vision-intensive":[26,134],"tasks":[27],"like":[28,136],"geometric":[29,64,102,114],"reasoning,":[30],"MLLMs":[31,75],"hallucinate":[32],"frequently,":[33],"leading":[34],"to":[35,40,108,123,132],"inaccurate":[36],"reasoning.We":[37],"attribute":[38],"this":[39,86],"perceptual":[42,143],"bottleneck":[43],"MLLMs,":[45],"which":[46],"caps":[47],"benefits":[49],"training.To":[52,84],"quantify":[53],"this,":[54],"we":[55,88],"design":[56],"a":[57,90],"Geo-Perception":[58],"Question-Answering":[59],"(GeoPQA)":[60],"benchmark,":[61],"targeting":[62],"basic":[63],"concepts":[65],"and":[66,118],"spatial":[67],"relationships.Experiments":[68],"GeoPQA":[70],"reveal":[71],"significant":[72],"shortcomings":[73],"visual":[77,99],"perception,":[78],"constraining":[79],"RL":[80,92],"reward":[81],"signals":[82],"for":[83],"address":[85],"bottleneck,":[87],"propose":[89],"two-stage":[91,111],"training":[93,112,127],"framework":[94],"by":[95,116,120],"first":[96],"enhancing":[97],"perception":[100],"structures,":[103],"then":[104],"fostering":[105],"capabilities.Applied":[107],"Qwen2.5-VL-3B-Instruct,":[109],"our":[110],"improves":[113],"9.7%":[117],"problem-solving":[119],"9.1%,":[121],"compared":[122],"direct":[125],"approach.Our":[128],"method":[129],"also":[130],"generalizes":[131],"other":[133],"domains":[135],"figure":[137],"understanding,":[138],"highlighting":[139],"importance":[141],"grounding":[144],"effective":[146],"MLLM":[147],"reasoning.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}