{"id":"https://openalex.org/W4416034754","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.635","title":"Do What? Teaching Vision-Language-Action Models to Reject the Impossible","display_name":"Do What? Teaching Vision-Language-Action Models to Reject the Impossible","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034754","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.635"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.635","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.635","pdf_url":"https://aclanthology.org/2025.findings-emnlp.635.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: EMNLP 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-emnlp.635.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113394063","display_name":"Wen-Han Hsieh","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen-Han Hsieh","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112737249","display_name":"E. R. Hsieh","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elvis Hsieh","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021184639","display_name":"Dantong Niu","orcid":"https://orcid.org/0009-0006-7421-5858"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dantong Niu","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029105520","display_name":"Trevor Darrell","orcid":"https://orcid.org/0000-0001-5453-8533"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevor Darrell","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066997569","display_name":"Roei Herzig","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roei Herzig","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104260047","display_name":"David M. Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David M. Chan","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"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":"11861","last_page":"11869"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.03310000151395798,"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"}},"topics":[{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.03310000151395798,"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"}},{"id":"https://openalex.org/T12694","display_name":"Categorization, perception, and language","score":0.025100000202655792,"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"}},{"id":"https://openalex.org/T12616","display_name":"Religious Education and Schools","score":0.018400000408291817,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2567000091075897},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2362000048160553},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.23080000281333923},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.22679999470710754},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.21199999749660492}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4521999955177307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29429998993873596},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.2833999991416931},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2362000048160553},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.23080000281333923},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.22679999470710754},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.21580000221729279},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.21199999749660492},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.20919999480247498}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.635","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.635","pdf_url":"https://aclanthology.org/2025.findings-emnlp.635.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.635","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.635","pdf_url":"https://aclanthology.org/2025.findings-emnlp.635.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034754.pdf","grobid_xml":"https://content.openalex.org/works/W4416034754.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"Vision-Language-Action":[1],"(VLA)":[2],"models":[3,14],"have":[4],"demonstrated":[5],"strong":[6],"performance":[7],"on":[8,16],"a":[9,23,87,110,121,134,179,220],"range":[10],"of":[11,125,206,213],"robotic":[12],"tasks.These":[13],"rely":[15],"multimodal":[17],"inputs,":[18],"with":[19,115],"language":[20,59,117,150],"instructions":[21],"playing":[22],"crucial":[24],"role-not":[25],"only":[26],"in":[27,32,92,102,170,222],"predicting":[28],"actions,":[29],"but":[30],"also":[31],"robustly":[33],"interpreting":[34],"user":[35],"intent,":[36],"even":[37],"when":[38,79],"the":[39,68,188,192,202,207,211,214,223,228],"requests":[40],"are":[41,178,198],"impossible":[42],"to":[43,56,86],"fulfill.In":[44],"this":[45,106],"work,":[46],"we":[47,108],"investigate":[48],"how":[49],"VLAs":[50],"can":[51,156],"recognize,":[52],"interpret,":[53],"and":[54,97,104,119,129,142,148,191,210],"respond":[55],"false-premise":[57,143,171],"instructions-natural":[58],"commands":[60],"that":[61,76,154],"reference":[62],"objects":[63],"or":[64,95],"conditions":[65],"absent":[66],"from":[67],"environment.We":[69],"propose":[70],"-Instruct-Verify-and-Act":[71],"(IVA)":[72],"-a":[73],"unified":[74],"framework":[75],"(i)":[77],"detects":[78],"an":[80],"instruction":[81,112],"cannot":[82],"be":[83],"executed":[84],"due":[85],"false":[88,158],"premise,":[89],"(ii)":[90],"engages":[91],"language-based":[93],"clarification":[94],"correction,":[96],"(iii)":[98],"grounds":[99],"plausible":[100],"alternatives":[101],"perception":[103],"action.Towards":[105],"end,":[107],"construct":[109],"large-scale":[111],"tuning":[113],"setup":[114],"structured":[116],"prompts":[118],"train":[120],"VLA":[122],"model":[123],"capable":[124],"handling":[126],"both":[127],"accurate":[128],"erroneous":[130],"requests.Our":[131],"approach":[132],"leverages":[133],"contextually":[135],"augmented,":[136],"semisynthetic":[137],"dataset":[138],"containing":[139],"paired":[140],"positive":[141],"instructions,":[144],"enabling":[145],"robust":[146],"detection":[147,160],"natural":[149],"correction.Our":[151],"experiments":[152],"show":[153],"IVA":[155],"improves":[157],"premise":[159],"accuracy":[161],"by":[162,173],"97.56%":[163],"over":[164],"baselines,":[165],"while":[166],"increasing":[167],"successful":[168],"responses":[169],"scenarios":[172],"50.78%.":[174],"*":[175],"Equal":[176],"contributionYou":[177],"Franka":[180],"robot":[181],"using":[182],"end-effector":[183],"control.The":[184],"task":[185],"is":[186],"\"open":[187],"middle":[189,229],"bottle\",":[190],"previous":[193],"five":[194],"(including":[195],"current)":[196],"steps":[197],"[[-0.1060,0.1280,-0.0767,]].Can":[199],"you":[200,226],"predict":[201],"2-D":[203],"visual":[204],"trace":[205],"end":[208],"effector":[209],"action":[212],"next":[215],"1":[216],"step?I":[217],"couldn't":[218],"find":[219],"bottle":[221],"current":[224],"scene.Do":[225],"mean":[227],"drawer":[230],"instead?":[231]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-11-08T00:00:00"}