{"id":"https://openalex.org/W7166844147","doi":"https://doi.org/10.18653/v1/2026.findings-acl.850","title":"Chain-of-Procedure: Hierarchical Visual-Language Reasoning for Procedural QA","display_name":"Chain-of-Procedure: Hierarchical Visual-Language Reasoning for Procedural QA","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166844147","doi":"https://doi.org/10.18653/v1/2026.findings-acl.850"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.850","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.850","pdf_url":"https://aclanthology.org/2026.findings-acl.850.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.850.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139763038","display_name":"Guanhua Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guanhua Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139732354","display_name":"Yutong Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yutong Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136250750","display_name":"Shenghe Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shenghe Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116569508","display_name":"Ci-Jun Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ci-jun Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139837414","display_name":"Shudong Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shudong Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139730297","display_name":"Lidia S. Chao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lidia S. Chao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869144","display_name":"Feng Wan","orcid":"https://orcid.org/0000-0002-8110-3460"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng Wan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139722114","display_name":"Derek F. Wong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Derek F. Wong","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":0.83415789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17207","last_page":"17224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.18719999492168427,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.18719999492168427,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.15469999611377716,"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":0.12680000066757202,"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/expert-system","display_name":"Expert system","score":0.2678000032901764},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.2597000002861023},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.24390000104904175},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.24169999361038208},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.23759999871253967}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6258000135421753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5026999711990356},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3361999988555908},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.24390000104904175},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24169999361038208},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.23759999871253967},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.23090000450611115},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.22789999842643738}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.850","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.850","pdf_url":"https://aclanthology.org/2026.findings-acl.850.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.850","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.850","pdf_url":"https://aclanthology.org/2026.findings-acl.850.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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.485512375831604}],"awards":[{"id":"https://openalex.org/G4615181649","display_name":null,"funder_award_id":"62266013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5893188460","display_name":null,"funder_award_id":"0007/2024/AKP","funder_id":"https://openalex.org/F4320323893","funder_display_name":"Fundo para o Desenvolvimento das Ci\u00eancias e da Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320311133","display_name":"United Mitochondrial Disease Foundation","ror":"https://ror.org/0528q0t18"},{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323893","display_name":"Fundo para o Desenvolvimento das Ci\u00eancias e da Tecnologia","ror":"https://ror.org/05vna4324"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166844147.pdf","grobid_xml":"https://content.openalex.org/works/W7166844147.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,70],"vision-language":[3],"models":[4],"(VLMs)":[5],"have":[6],"achieved":[7],"impressive":[8],"results":[9],"on":[10,46],"standard":[11,137],"image-text":[12],"tasks,":[13],"yet":[14],"their":[15],"potential":[16],"for":[17,37,59],"visual":[18,60,80,109],"procedure":[19],"question":[20],"answering":[21],"(VP-QA)":[22],"remains":[23],"largely":[24],"unexplored.VP-QA":[25],"presents":[26],"unique":[27],"challenges":[28],"where":[29],"users":[30],"query":[31],"next-step":[32],"actions":[33],"by":[34],"uploading":[35],"images":[36],"intermediate":[38],"states":[39],"of":[40,76],"complex":[41],"procedures.To":[42],"systematically":[43],"evaluate":[44],"VLMs":[45,126],"this":[47],"practical":[48],"task,":[49],"we":[50,65,95],"propose":[51],"ProcedureVQA,":[52],"a":[53,99],"novel":[54],"multimodal":[55],"benchmark":[56],"specifically":[57],"designed":[58],"procedural":[61],"reasoning.Through":[62],"comprehensive":[63],"analysis,":[64],"identify":[66],"two":[67],"critical":[68],"limitations":[69],"current":[71],"VLMs:":[72],"inadequate":[73],"cross-modal":[74],"retrieval":[75],"structured":[77],"procedures":[78],"given":[79],"states,":[81],"and":[82,88,118],"misalignment":[83],"between":[84],"image":[85],"sequence":[86],"granularity":[87],"textual":[89],"step":[90,113],"decomposition.To":[91],"address":[92],"these":[93],"issues,":[94],"present":[96],"Chainof-Procedure":[97],"(CoP),":[98],"hierarchical":[100],"reasoning":[101],"framework":[102],"that":[103],"first":[104],"retrieves":[105],"relevant":[106],"instructions":[107],"using":[108],"cues,":[110],"then":[111],"performs":[112],"refinement":[114],"through":[115],"semantic":[116],"decomposition,":[117],"finally":[119],"generates":[120],"the":[121],"next":[122],"step.Experiments":[123],"across":[124],"six":[125],"demonstrate":[127],"CoP's":[128],"effectiveness,":[129],"achieving":[130],"up":[131],"to":[132],"13%":[133],"absolute":[134],"improvement":[135],"over":[136],"baselines.":[138]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}