{"id":"https://openalex.org/W7166845935","doi":"https://doi.org/10.18653/v1/2026.findings-acl.399","title":"LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals","display_name":"LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166845935","doi":"https://doi.org/10.18653/v1/2026.findings-acl.399"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.399","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.399","pdf_url":"https://aclanthology.org/2026.findings-acl.399.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.399.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123215181","display_name":"Gilat Toker","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Gilat Toker","raw_affiliation_strings":["Faculty of Data and Decision Sciences , Technion -Israel Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Data and Decision Sciences , Technion -Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139839767","display_name":"Nitay Calderon","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Nitay Calderon","raw_affiliation_strings":["Faculty of Data and Decision Sciences , Technion -Israel Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Data and Decision Sciences , Technion -Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008160776","display_name":"Ohad Amosy","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ohad Amosy","raw_affiliation_strings":["Faculty of Data and Decision Sciences , Technion -Israel Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Data and Decision Sciences , Technion -Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139789181","display_name":"Roi Reichart","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Roi Reichart","raw_affiliation_strings":["Faculty of Data and Decision Sciences , Technion -Israel Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Data and Decision Sciences , Technion -Israel Institute of Technology","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8357804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8149","last_page":"8186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.6316999793052673,"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":0.6316999793052673,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.06909999996423721,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.03709999844431877,"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/counterfactual-conditional","display_name":"Counterfactual conditional","score":0.6922000050544739},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5157999992370605},{"id":"https://openalex.org/keywords/causation","display_name":"Causation","score":0.4634000062942505},{"id":"https://openalex.org/keywords/causality","display_name":"Causality (physics)","score":0.4381999969482422},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.37860000133514404},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.33820000290870667}],"concepts":[{"id":"https://openalex.org/C71889745","wikidata":"https://www.wikidata.org/wiki/Q1783264","display_name":"Counterfactual conditional","level":3,"score":0.6922000050544739},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5157999992370605},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.4652999937534332},{"id":"https://openalex.org/C166151441","wikidata":"https://www.wikidata.org/wiki/Q4923601","display_name":"Causation","level":2,"score":0.4634000062942505},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.4381999969482422},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C118084267","wikidata":"https://www.wikidata.org/wiki/Q26110","display_name":"Positive economics","level":1,"score":0.36309999227523804},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2775999903678894},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2754000127315521},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.27390000224113464},{"id":"https://openalex.org/C100001284","wikidata":"https://www.wikidata.org/wiki/Q2248246","display_name":"Public economics","level":1,"score":0.2624000012874603},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.260699987411499},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2563000023365021},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.25619998574256897},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.25450000166893005},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.399","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.399","pdf_url":"https://aclanthology.org/2026.findings-acl.399.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.399","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.399","pdf_url":"https://aclanthology.org/2026.findings-acl.399.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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166845935.pdf","grobid_xml":"https://content.openalex.org/works/W7166845935.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Concept-based":[0],"explanations":[1,27],"quantify":[2],"how":[3],"highlevel":[4],"concepts":[5],"(e.g.,":[6],"gender":[7],"or":[8],"experience)":[9],"influence":[10],"model":[11,143],"behavior,":[12],"which":[13],"is":[14,74],"crucial":[15],"for":[16,58,69,134,169],"decision-makers":[17],"in":[18,76],"high-stakes":[19],"domains.Recent":[20],"work":[21],"evaluates":[22],"the":[23,84,93,99],"faithfulness":[24],"of":[25,83,125,142],"such":[26],"by":[28],"comparing":[29],"them":[30],"to":[31,145,156,161],"reference":[32],"causal":[33],"effects":[34],"estimated":[35],"from":[36],"counterfactuals.In":[37],"practice,":[38],"existing":[39],"benchmarks":[40],"rely":[41],"on":[42,88],"costly":[43],"human-written":[44],"counterfactuals":[45],"that":[46,149],"serve":[47],"as":[48],"an":[49,96],"imperfect":[50],"proxy.To":[51],"address":[52],"this,":[53],"we":[54,120,147],"introduce":[55,101],"a":[56,89,114,122,166],"framework":[57],"constructing":[59],"datasets":[60,103],"containing":[61],"structural":[62],"counterfactual":[63],"pairs:":[64],"LIB-ERTy":[65],"(LLM-based":[66],"Interventional":[67],"Benchmark":[68],"Explainability":[70],"with":[71,113],"Reference":[72],"Targets).LIBERTy":[73],"grounded":[75],"explicitly":[77],"defined":[78],"Structured":[79],"Causal":[80],"Models":[81],"(SCMs)":[82],"text":[85],"generation,":[86],"interventions":[87],"concept":[90],"propagate":[91],"through":[92],"SCM":[94],"until":[95],"LLM":[97],"generates":[98],"counterfactual.We":[100],"three":[102],"(disease":[104],"detection,":[105],"CV":[106],"screening,":[107],"and":[108,130],"workplace":[109],"violence":[110],"prediction)":[111],"together":[112],"new":[115],"evaluation":[116],"metric,":[117],"order-faithfulness.Using":[118],"them,":[119],"evaluate":[121],"wide":[123],"range":[124],"methods":[126],"across":[127],"five":[128],"models":[129],"identify":[131],"substantial":[132],"headroom":[133],"improving":[135],"concept-based":[136],"explanations.LIBERTy":[137],"also":[138],"enables":[139],"systematic":[140],"analysis":[141],"sensitivity":[144,155],"interventions:":[146],"find":[148],"proprietary":[150],"LLMs":[151],"show":[152],"markedly":[153],"reduced":[154],"demographic":[157],"concepts,":[158],"likely":[159],"due":[160],"post-training":[162],"mitigation.Overall,":[163],"LIBERTy":[164],"provides":[165],"much-needed":[167],"benchmark":[168],"developing":[170],"faithful":[171],"explainability":[172],"methods.":[173],"1":[174],"Box":[175],"3.":[176]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}