{"id":"https://openalex.org/W7166798998","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1196","title":"UnAC: Adaptive Visual Prompting with Abstraction and Stepwise Checking for Complex Multimodal Reasoning","display_name":"UnAC: Adaptive Visual Prompting with Abstraction and Stepwise Checking for Complex Multimodal Reasoning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166798998","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1196"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1196","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1196","pdf_url":"https://aclanthology.org/2026.findings-acl.1196.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 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1196.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139746013","display_name":"Yifan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139758560","display_name":"Yun Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun Fu","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85637608,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23884","last_page":"23893"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8046000003814697,"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":0.8046000003814697,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.059700001031160355,"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/T12031","display_name":"Speech and dialogue systems","score":0.04089999943971634,"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/abstraction","display_name":"Abstraction","score":0.6517999768257141},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.29409998655319214},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.2791000008583069},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.27379998564720154},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.2732999920845032}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.670199990272522},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6517999768257141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5146999955177307},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3447999954223633},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3255000114440918},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2793999910354614},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2551000118255615},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1196","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1196","pdf_url":"https://aclanthology.org/2026.findings-acl.1196.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 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1196","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1196","pdf_url":"https://aclanthology.org/2026.findings-acl.1196.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 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166798998.pdf","grobid_xml":"https://content.openalex.org/works/W7166798998.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Although":[0],"recent":[1],"LMMs":[2,43,66],"have":[3],"become":[4],"much":[5],"stronger":[6],"at":[7],"visual":[8,20,61],"perception,":[9],"they":[10],"remain":[11],"unreliable":[12],"on":[13,69,103],"problems":[14],"that":[15,35,64,91],"require":[16],"multi-step":[17],"reasoning":[18,37,93],"over":[19],"evidence.In":[21],"this":[22],"paper,":[23],"we":[24,57,85],"present":[25],"UnAC":[26],"(Understanding,":[27],"Abstracting,":[28],"and":[29,48,53,99,108],"Checking),":[30],"a":[31,87],"multimodal":[32,40],"prompting":[33,62],"method":[34],"strengthens":[36],"for":[38],"complex":[39],"tasks":[41],"in":[42],"(e.g.,":[44],"GPT-4o,":[45],"Gemini":[46],"1.5,":[47],"GPT-4V).To":[49],"improve":[50],"image":[51],"understanding":[52],"capture":[54],"fine":[55],"details,":[56],"propose":[58],"an":[59,74],"adaptive":[60],"strategy":[63],"enables":[65],"to":[67,77],"focus":[68],"salient":[70],"regions.We":[71],"further":[72],"design":[73],"image-abstraction":[75],"prompt":[76],"effectively":[78],"extract":[79],"key":[80],"information":[81],"from":[82],"images.In":[83],"addition,":[84],"introduce":[86],"gradual":[88],"self-checking":[89],"scheme":[90],"improves":[92],"by":[94],"verifying":[95],"each":[96],"decomposed":[97],"subquestion":[98],"its":[100],"answer.Extensive":[101],"experiments":[102],"three":[104],"public":[105],"benchmarks-MathVista,":[106],"MM-Vet,":[107],"MMMU.":[109]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}