{"id":"https://openalex.org/W7204208464","doi":"https://doi.org/10.48550/arxiv.2608.23518","title":"Investigating Relational Reasoning in VLMs","display_name":"Investigating Relational Reasoning in VLMs","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204208464","doi":"https://doi.org/10.48550/arxiv.2608.23518"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.23518","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23518","pdf_url":"https://arxiv.org/pdf/2608.23518","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.23518","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148106231","display_name":"Adhithya Laxman Ravi Shankar Geetha","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geetha, Adhithya Laxman Ravi Shankar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148126882","display_name":"Aulia Kharis Rakhmasari","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Rakhmasari, Aulia Kharis","raw_affiliation_strings":["Department of Computer Science , ETH Zurich , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , ETH Zurich , Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148133247","display_name":"Haleema Ramzan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ramzan, Haleema","raw_affiliation_strings":["Department of Computer Science , ETH Zurich , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , ETH Zurich , Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130579175","display_name":"Xander Yap","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Yap, Xander","raw_affiliation_strings":["Department of Computer Science , ETH Zurich , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , ETH Zurich , Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9729999899864197},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"visual reasoning","score":0.7049999833106995},{"id":"https://openalex.org/keywords/relational-reasoning","display_name":"relational reasoning","score":0.9139999747276306},{"id":"https://openalex.org/keywords/shortcut-learning","display_name":"shortcut learning","score":0.8029999732971191},{"id":"https://openalex.org/keywords/language-cues","display_name":"language cues","score":0.9110000133514404},{"id":"https://openalex.org/keywords/causal-reasoning","display_name":"causal reasoning","score":0.503000020980835},{"id":"https://openalex.org/keywords/model-interpretability","display_name":"model interpretability","score":0.5529999732971191}],"concepts":[{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.7282999753952026},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6987000107765198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5946000218391418},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.5709999799728394},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5080999732017517},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.47690001130104065},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.4246000051498413},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28859999775886536},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2711000144481659},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.26759999990463257},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26190000772476196},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2554999887943268},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.23518","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23518","pdf_url":"https://arxiv.org/pdf/2608.23518","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.23518","doi":"https://doi.org/10.48550/arxiv.2608.23518","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.23518","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.23518","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23518","pdf_url":"https://arxiv.org/pdf/2608.23518","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204208464.pdf","grobid_xml":"https://content.openalex.org/works/W7204208464.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2529194139","https://openalex.org/W2953337107","https://openalex.org/W4389518760","https://openalex.org/W4402727764","https://openalex.org/W4402753913","https://openalex.org/W4403818822","https://openalex.org/W4416780398"],"related_works":["https://openalex.org/W7221023131","https://openalex.org/W4402353855","https://openalex.org/W7117312522","https://openalex.org/W4414893770","https://openalex.org/W4377865926","https://openalex.org/W4392617694","https://openalex.org/W4415966298","https://openalex.org/W4393027669","https://openalex.org/W7214758169","https://openalex.org/W4416832895"],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"achieve":[3],"strong":[4],"performance":[5],"in":[6,102],"visual":[7,17,46,85,95],"reasoning":[8,96],"tasks,":[9],"but":[10],"it":[11],"remains":[12],"unclear":[13],"whether":[14],"they":[15],"understand":[16],"relations,":[18],"or":[19,27],"simply":[20],"employ":[21],"shortcuts":[22],"such":[23],"as":[24],"language":[25,73,103],"cues":[26],"priors.":[28],"To":[29],"investigate":[30],"this,":[31,53],"we":[32,54],"use":[33],"the":[34,76],"Qwen3-VL-4B":[35],"(Bai":[36],"et":[37],"al.,":[38],"2025),":[39],"a":[40,56],"modern":[41],"VLM,":[42],"to":[43,70,80],"decode":[44],"how":[45],"information":[47],"is":[48,78],"encoded":[49],"across":[50],"depths.":[51],"For":[52],"propose":[55],"synthetic":[57],"dataset":[58,77],"of":[59],"simple":[60],"geometric":[61],"shapes":[62],"for":[63],"controlled":[64],"analysis,":[65],"along":[66],"with":[67,97],"queries":[68],"crafted":[69],"precisely":[71],"test":[72,81],"cues.":[74,104],"Furthermore,":[75],"modified":[79],"causal":[82],"reliance":[83],"on":[84],"evidence.":[86],"Our":[87],"results":[88],"show":[89],"that":[90],"current":[91],"VLMs":[92],"combine":[93],"genuine":[94],"shortcut":[98],"strategies":[99],"primarily":[100],"rooted":[101]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-26T00:00:00"}