{"id":"https://openalex.org/W4408353821","doi":"https://doi.org/10.1109/icassp49660.2025.10888462","title":"Do Multimodal Language Models Really Understand Direction? A Benchmark for Compass Direction Reasoning","display_name":"Do Multimodal Language Models Really Understand Direction? A Benchmark for Compass Direction Reasoning","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353821","doi":"https://doi.org/10.1109/icassp49660.2025.10888462"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5067144254","display_name":"Hang Yin","orcid":"https://orcid.org/0000-0002-3599-440X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hang Yin","raw_affiliation_strings":["Beijing Institute of Technology,Department of Computer Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002538109","display_name":"Zhifeng Lin","orcid":"https://orcid.org/0009-0002-4605-2802"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifeng Lin","raw_affiliation_strings":["Beijing Institute of Technology,Department of Computer Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027021748","display_name":"Xin Liu","orcid":"https://orcid.org/0000-0002-7658-284X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":["Beijing Institute of Technology,Department of Computer Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641761","display_name":"Bin Sun","orcid":"https://orcid.org/0000-0002-7029-8784"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Sun","raw_affiliation_strings":["Beijing Institute of Technology,Department of Computer Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100342150","display_name":"Kan Li","orcid":"https://orcid.org/0000-0002-1618-919X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kan Li","raw_affiliation_strings":["Beijing Institute of Technology,Department of Computer Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5067144254"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":6.5456,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.9578557,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.986299991607666,"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/T12031","display_name":"Speech and dialogue systems","score":0.986299991607666,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9513000249862671,"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/T11148","display_name":"Language, Metaphor, and Cognition","score":0.9175999760627747,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/compass","display_name":"Compass","score":0.8763845562934875},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7226378917694092},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6880708336830139},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5372011661529541},{"id":"https://openalex.org/keywords/cardinal-direction","display_name":"Cardinal direction","score":0.4446891248226166},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3431228995323181},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.11101686954498291},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.1021575927734375}],"concepts":[{"id":"https://openalex.org/C2778361833","wikidata":"https://www.wikidata.org/wiki/Q34735","display_name":"Compass","level":2,"score":0.8763845562934875},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7226378917694092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6880708336830139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5372011661529541},{"id":"https://openalex.org/C197902243","wikidata":"https://www.wikidata.org/wiki/Q23718","display_name":"Cardinal direction","level":2,"score":0.4446891248226166},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3431228995323181},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.11101686954498291},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.1021575927734375},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1424654272","https://openalex.org/W2083377175","https://openalex.org/W2112040437","https://openalex.org/W2128092632","https://openalex.org/W3153839026","https://openalex.org/W4224266081","https://openalex.org/W4249244053","https://openalex.org/W4312922092","https://openalex.org/W4381802186","https://openalex.org/W4389520747","https://openalex.org/W4389520792","https://openalex.org/W4391979508","https://openalex.org/W4392679398","https://openalex.org/W4393156822","https://openalex.org/W4396546852","https://openalex.org/W4402727764","https://openalex.org/W6791353385","https://openalex.org/W6851592950","https://openalex.org/W6857470917","https://openalex.org/W6857611658","https://openalex.org/W6861910683"],"related_works":["https://openalex.org/W4390719984","https://openalex.org/W2270942133","https://openalex.org/W3160767377","https://openalex.org/W3204019825","https://openalex.org/W3021626027","https://openalex.org/W4250287183","https://openalex.org/W4252892293","https://openalex.org/W2048921457","https://openalex.org/W2066113632","https://openalex.org/W2037798658"],"abstract_inverted_index":{"Direction":[0,32],"reasoning":[1,22,41,121],"is":[2],"essential":[3],"for":[4],"intelligent":[5],"systems":[6],"to":[7,37,53,133],"understand":[8,134],"the":[9,30,39,105,130],"real":[10],"world.":[11],"While":[12],"existing":[13],"work":[14],"focuses":[15],"primarily":[16],"on":[17],"spatial":[18,55],"reasoning,":[19,76,128],"compass":[20,61,119],"direction":[21,40,75,120,135],"remains":[23],"underexplored.":[24],"To":[25],"address":[26],"this,":[27],"we":[28],"propose":[29],"Compass":[31],"Reasoning":[33],"(CDR)":[34],"benchmark,":[35],"designed":[36],"evaluate":[38],"capabilities":[42],"of":[43,99,107],"multimodal":[44],"language":[45],"models":[46],"(MLMs).":[47],"CDR":[48,89],"includes":[49],"three":[50],"types":[51],"images":[52],"test":[54],"(up,":[56],"down,":[57],"left,":[58],"right)":[59],"and":[60,109,126],"(north,":[62],"south,":[63],"east,":[64],"west)":[65],"directions.":[66],"Our":[67],"evaluation":[68],"reveals":[69],"that":[70,85],"most":[71],"MLMs":[72],"struggle":[73],"with":[74,88],"often":[77],"performing":[78],"at":[79],"random":[80],"guessing":[81],"levels.":[82],"Experiments":[83],"show":[84],"training":[86],"directly":[87],"data":[90,125],"yields":[91],"limited":[92],"improvements,":[93],"as":[94],"it":[95],"requires":[96],"an":[97],"understanding":[98],"real-world":[100],"physical":[101],"rules.":[102],"We":[103],"explore":[104],"impact":[106],"mixdata":[108],"CoT":[110],"fine-tuning":[111],"methods,":[112],"which":[113],"significantly":[114],"enhance":[115],"MLM":[116],"performance":[117],"in":[118],"by":[122],"incorporating":[123],"diverse":[124],"step-by-step":[127],"improving":[129],"model\u2019s":[131],"ability":[132],"relationships.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}