{"id":"https://openalex.org/W4412888939","doi":"https://doi.org/10.18653/v1/2025.findings-acl.2","title":"Beyond Perception: Evaluating Abstract Visual Reasoning through Multi-Stage Task","display_name":"Beyond Perception: Evaluating Abstract Visual Reasoning through Multi-Stage Task","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888939","doi":"https://doi.org/10.18653/v1/2025.findings-acl.2"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.2","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.2","pdf_url":"https://aclanthology.org/2025.findings-acl.2.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: ACL 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-acl.2.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111270283","display_name":"Yanbei Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanbei Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074613052","display_name":"Yihao Ding","orcid":"https://orcid.org/0000-0001-5065-6911"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yihao Ding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101366154","display_name":"Chao Lei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051951717","display_name":"Jiayang Ao","orcid":"https://orcid.org/0000-0001-6416-1215"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiayang Ao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032767467","display_name":"Jey Han Lau","orcid":"https://orcid.org/0000-0002-1647-4628"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jey Han Lau","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084653483","display_name":"Krista A. Ehinger","orcid":"https://orcid.org/0000-0003-2247-3020"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krista A. Ehinger","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":"13","last_page":"45"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11122","display_name":"Online Learning and Analytics","score":0.8726000189781189,"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"}},"topics":[{"id":"https://openalex.org/T11122","display_name":"Online Learning and Analytics","score":0.8726000189781189,"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"}},{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.8683000206947327,"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/T11516","display_name":"Visual and Cognitive Learning Processes","score":0.8539000153541565,"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/computer-science","display_name":"Computer science","score":0.7461133599281311},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6798422336578369},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.656110405921936},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.5879412293434143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4350828230381012},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4153297543525696},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39009934663772583},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16159692406654358},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08859202265739441},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.07120472192764282},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.05179053544998169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7461133599281311},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6798422336578369},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.656110405921936},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.5879412293434143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4350828230381012},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4153297543525696},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39009934663772583},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16159692406654358},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08859202265739441},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.07120472192764282},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.05179053544998169},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.2","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.2","pdf_url":"https://aclanthology.org/2025.findings-acl.2.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: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.2","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.2","pdf_url":"https://aclanthology.org/2025.findings-acl.2.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: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888939.pdf","grobid_xml":"https://content.openalex.org/works/W4412888939.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2329386257","https://openalex.org/W2503350049","https://openalex.org/W2397616145","https://openalex.org/W2397320258","https://openalex.org/W4412054803","https://openalex.org/W4324058133","https://openalex.org/W4412277885","https://openalex.org/W2598946408","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"Current":[0],"Multimodal":[1],"Large":[2],"Language":[3],"Models":[4],"(MLLMs)":[5],"excel":[6],"in":[7,14,116,151],"general":[8],"visual":[9],"reasoning":[10,22,46,77],"but":[11,40,55],"remain":[12],"underexplored":[13],"Abstract":[15],"Visual":[16],"Reasoning":[17],"(AVR),":[18],"which":[19,109],"demands":[20],"higher-order":[21],"to":[23,75,118,148],"identify":[24],"abstract":[25],"rules":[26],"beyond":[27],"simple":[28],"perception.Existing":[29],"AVR":[30,70],"benchmarks":[31],"focus":[32,88],"on":[33,73,89,125,142],"single-step":[34],"reasoning,":[35],"emphasizing":[36],"the":[37,42,90,98,111,119],"end":[38],"result":[39],"neglecting":[41],"multi-stage":[43],"nature":[44],"of":[45,81,100,113],"process.Past":[47],"studies":[48],"found":[49],"MLLMs":[50,139],"struggle":[51],"with":[52],"these":[53],"benchmarks,":[54],"it":[56],"doesn't":[57],"explain":[58],"how":[59],"they":[60,146],"fail.To":[61],"address":[62],"this":[63],"gap,":[64],"we":[65,103],"introduce":[66],"MultiStAR,":[67],"a":[68,105],"Multi-Stage":[69],"benchmark":[71],"based":[72],"RAVEN,":[74],"assess":[76],"across":[78],"varying":[79],"levels":[80],"complexity.Additionally,":[82],"existing":[83,138],"metrics":[84],"like":[85],"accuracy":[86],"only":[87],"final":[91,120],"outcomes":[92],"while":[93,137],"do":[94],"not":[95],"account":[96],"for":[97],"correctness":[99,112],"intermediate":[101,114],"steps.Therefore,":[102],"propose":[104],"novel":[106],"metric,":[107],"MSEval,":[108],"considers":[110],"steps":[115],"addition":[117],"outcomes.We":[121],"conduct":[122],"comprehensive":[123],"experiments":[124],"MultiStAR":[126],"using":[127],"17":[128],"representative":[129],"close-source":[130],"and":[131,158],"opensource":[132],"MLLMs.The":[133],"results":[134],"reveal":[135],"that":[136],"perform":[140],"adequately":[141],"basic":[143],"perception":[144],"tasks,":[145],"continue":[147],"face":[149],"challenges":[150],"more":[152],"complex":[153],"rule":[154],"detection":[155],"stages.The":[156],"dataset":[157],"code":[159],"are":[160],"available":[161],"at":[162],"https://github.com/YanbeiJiang/MultiStAR":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
