{"id":"https://openalex.org/W7212072012","doi":"https://doi.org/10.18653/2026.blackboxnlp-1.60","title":"Limitations of Automated Simulatability: LLM Simulators Can Bypass Explanations","display_name":"Limitations of Automated Simulatability: LLM Simulators Can Bypass Explanations","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7212072012","doi":"https://doi.org/10.18653/2026.blackboxnlp-1.60"},"language":"en","primary_location":{"id":"doi:10.18653/2026.blackboxnlp-1.60","doi":"https://doi.org/10.18653/2026.blackboxnlp-1.60","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.blackboxnlp-1.60","pdf_url":"https://aclanthology.org/2026.blackboxnlp-1.60.pdf","source":{"id":"https://openalex.org/S7407088969","display_name":"BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.blackboxnlp-1.60.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008810156","display_name":"Antonin Poch\u00e9","orcid":"https://orcid.org/0009-0000-0930-3313","observed_orcids":["https://orcid.org/0009-0000-0930-3313"]},"institutions":[{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]},{"id":"https://openalex.org/I4394709072","display_name":"IRT Saint Exup\u00e9ry","ror":"https://ror.org/01qew1n19","country_code":"FR","type":"nonprofit","lineage":["https://openalex.org/I4394709072"]},{"id":"https://openalex.org/I4405258862","display_name":"Universit\u00e9 de Toulouse","ror":"https://ror.org/01ahyrz84","country_code":"FR","type":"education","lineage":["https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antonin Poch\u00e9","raw_affiliation_strings":["IRIT , Universit\u00e9 de Toulouse ,","IRT Saint Exup\u00e9ry ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IRIT , Universit\u00e9 de Toulouse ,","institution_ids":["https://openalex.org/I4210119061","https://openalex.org/I4405258862"]},{"raw_affiliation_string":"IRT Saint Exup\u00e9ry ,","institution_ids":["https://openalex.org/I4394709072"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059933120","display_name":"Fanny Jourdan","orcid":"https://orcid.org/0009-0002-9356-4907","observed_orcids":["https://orcid.org/0009-0002-9356-4907","https://orcid.org/0009-0006-4920-2406"]},"institutions":[{"id":"https://openalex.org/I4394709072","display_name":"IRT Saint Exup\u00e9ry","ror":"https://ror.org/01qew1n19","country_code":"FR","type":"nonprofit","lineage":["https://openalex.org/I4394709072"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fanny Jourdan","raw_affiliation_strings":["IRT Saint Exup\u00e9ry ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IRT Saint Exup\u00e9ry ,","institution_ids":["https://openalex.org/I4394709072"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027823774","display_name":"Nils Feldhus","orcid":"https://orcid.org/0009-0008-7408-7483","observed_orcids":["https://orcid.org/0009-0008-7408-7483"]},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]},{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I4401727010","display_name":"Berlin Institute for the Foundations of Learning and Data","ror":"https://ror.org/05dsfb086","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4401727010","https://openalex.org/I4577782","https://openalex.org/I7877124"]}],"countries":["DE","NL"],"is_corresponding":false,"raw_author_name":"Nils Feldhus","raw_affiliation_strings":["DFKI , 8 BIFOLD ,","University of Groningen ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI , 8 BIFOLD ,","institution_ids":["https://openalex.org/I33256026","https://openalex.org/I4401727010"]},{"raw_affiliation_string":"University of Groningen ,","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122207433","display_name":"Qianli Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Qianli Wang","raw_affiliation_strings":["Technische Universit\u00e4t Berlin ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Berlin ,","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150897458","display_name":"Jing Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jing Yang","raw_affiliation_strings":["Technische Universit\u00e4t Berlin ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Berlin ,","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102820995","display_name":"Simon Ostermann","orcid":"https://orcid.org/0000-0002-0899-0657","observed_orcids":["https://orcid.org/0000-0002-0899-0657"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon Ostermann","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137758266","display_name":"Nicholas Asher","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]},{"id":"https://openalex.org/I4405258862","display_name":"Universit\u00e9 de Toulouse","ror":"https://ror.org/01ahyrz84","country_code":"FR","type":"education","lineage":["https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicholas Asher","raw_affiliation_strings":["CNRS","IRIT , Universit\u00e9 de Toulouse ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS","institution_ids":["https://openalex.org/I1294671590"]},{"raw_affiliation_string":"IRIT , Universit\u00e9 de Toulouse ,","institution_ids":["https://openalex.org/I4210119061","https://openalex.org/I4405258862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151082141","display_name":"Philippe Muller","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]},{"id":"https://openalex.org/I4405258862","display_name":"Universit\u00e9 de Toulouse","ror":"https://ror.org/01ahyrz84","country_code":"FR","type":"education","lineage":["https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Philippe Muller","raw_affiliation_strings":["IRIT , Universit\u00e9 de Toulouse ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IRIT , Universit\u00e9 de Toulouse ,","institution_ids":["https://openalex.org/I4210119061","https://openalex.org/I4405258862"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063295175","display_name":"Vera Schmitt","orcid":"https://orcid.org/0000-0002-9735-6956","observed_orcids":["https://orcid.org/0000-0002-9735-6956"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vera Schmitt","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"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":0.71580732,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1067","last_page":"1099"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":1.0,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":1.0,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0,"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/simulatability","display_name":"simulatability","score":0.7490000128746033},{"id":"https://openalex.org/keywords/evaluation-of-explanations","display_name":"explanation evaluation","score":0.7110000252723694},{"id":"https://openalex.org/keywords/shortcut-learning","display_name":"shortcut learning","score":0.7599999904632568}],"concepts":[{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.7688000202178955},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7093999981880188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6704999804496765},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5379999876022339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5117999911308289},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47279998660087585},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4523000121116638},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.43639999628067017},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.39239999651908875},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31700000166893005},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.blackboxnlp-1.60","doi":"https://doi.org/10.18653/2026.blackboxnlp-1.60","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.blackboxnlp-1.60","pdf_url":"https://aclanthology.org/2026.blackboxnlp-1.60.pdf","source":{"id":"https://openalex.org/S7407088969","display_name":"BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2609.08585","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.08585","pdf_url":"https://arxiv.org/pdf/2609.08585","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.08585","doi":"https://doi.org/10.48550/arxiv.2609.08585","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.08585","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":"doi:10.18653/2026.blackboxnlp-1.60","doi":"https://doi.org/10.18653/2026.blackboxnlp-1.60","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.blackboxnlp-1.60","pdf_url":"https://aclanthology.org/2026.blackboxnlp-1.60.pdf","source":{"id":"https://openalex.org/S7407088969","display_name":"BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212072012.pdf","grobid_xml":"https://content.openalex.org/works/W7212072012.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3035371891","https://openalex.org/W4406241273","https://openalex.org/W3102035862","https://openalex.org/W4390091993","https://openalex.org/W4416716135","https://openalex.org/W7133229034","https://openalex.org/W7163251886","https://openalex.org/W7119538405","https://openalex.org/W4384648622","https://openalex.org/W7203614400"],"abstract_inverted_index":{"Simulatability":[0],"is":[1,25],"an":[2],"evaluation":[3,24],"protocol":[4],"for":[5,43,94,134],"explanations":[6,93,128],"that":[7],"quantifies":[8],"their":[9],"usefulness":[10],"by":[11,78],"how":[12],"well":[13],"they":[14],"help":[15],"a":[16,19,100,105,113],"user":[17],"predict":[18],"task":[20,82,125],"model's":[21],"outputs.Since":[22],"human":[23,30],"costly,":[26],"automated":[27,137],"simulatability":[28,77,138],"replaces":[29],"explainees":[31],"with":[32,104,112],"LLM":[33],"simulators,":[34],"as":[35],"proposed":[36],"in":[37,116],"ConSim":[38],"(Poch\u00e9":[39],"et":[40],"al.,":[41],"2025)":[42],"large-scale":[44],"experiments.We":[45],"qualitatively":[46],"replicate":[47],"and":[48,61,64],"extend":[49],"ConSim's":[50],"ranking":[51],"of":[52],"explanation":[53,59],"methods":[54],"across":[55],"the":[56,80,87,96,117],"tested":[57,118],"datasets,":[58],"families,":[60],"simulator":[62,120],"LLMs,":[63],"identify":[65],"two":[66],"limitations.First,":[67],"when":[68],"class":[69,89],"names":[70],"are":[71,110],"meaningful,":[72],"simulators":[73],"can":[74,91],"obtain":[75],"high":[76],"solving":[79],"classification":[81],"directly,":[83],"without":[84],"relying":[85],"on":[86,124],"explanations.Second,":[88],"anonymization":[90],"reward":[92],"leaking":[95],"hidden":[97],"label":[98],"mapping,":[99],"limitation":[101],"we":[102],"expose":[103],"new":[106],"classes-as-concepts":[107],"baseline.These":[108],"results":[109],"consistent":[111],"shortcut":[114],"hypothesis:":[115],"settings,":[119],"predictions":[121],"mainly":[122],"rely":[123],"priors,":[126],"while":[127],"produce":[129],"small":[130],"changes.We":[131],"derive":[132],"recommendations":[133],"more":[135],"robust":[136],"evaluations.":[139]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-09-10T00:00:00"}
