{"id":"https://openalex.org/W7166824109","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1977","title":"STaD: Scaffolded Task Design for Identifying Compositional Skill Gaps in LLMs","display_name":"STaD: Scaffolded Task Design for Identifying Compositional Skill Gaps in LLMs","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166824109","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1977"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1977","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1977","pdf_url":"https://aclanthology.org/2026.findings-acl.1977.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.1977.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139719066","display_name":"Sungeun An","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sungeun An","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053049612","display_name":"Swanand Kadhe","orcid":"https://orcid.org/0000-0003-2006-1030"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Swanand Ravindra Kadhe","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031485134","display_name":"Shailja Thakur","orcid":"https://orcid.org/0000-0001-9590-5061"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shailja Thakur","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051321506","display_name":"Chad DeLuca","orcid":"https://orcid.org/0009-0009-7690-7454"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chad DeLuca","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102917997","display_name":"Hima Patel","orcid":"https://orcid.org/0000-0002-0031-8428"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hima Patel","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":0.81359719,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"39675","last_page":"39705"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.15839999914169312,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.15839999914169312,"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/T13034","display_name":"Information Systems Education and Curriculum Development","score":0.07450000196695328,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11122","display_name":"Online Learning and Analytics","score":0.04690000042319298,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/task","display_name":"Task (project management)","score":0.6489999890327454},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.2630999982357025},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.26080000400543213}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6489999890327454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45750001072883606},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3188999891281128},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3167000114917755},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2874999940395355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27469998598098755},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2630999982357025},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25699999928474426},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.24779999256134033}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1977","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1977","pdf_url":"https://aclanthology.org/2026.findings-acl.1977.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.1977","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1977","pdf_url":"https://aclanthology.org/2026.findings-acl.1977.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/W7166824109.pdf","grobid_xml":"https://content.openalex.org/works/W7166824109.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Benchmarks":[0],"are":[1],"often":[2],"used":[3],"as":[4,88],"a":[5,60,89],"standard":[6],"to":[7,28],"understand":[8],"LLM":[9,87],"capabilities":[10],"in":[11,59,104],"different":[12],"domains.However,":[13],"aggregate":[14],"benchmark":[15,46],"scores":[16],"provide":[17],"limited":[18],"insight":[19],"into":[20],"compositional":[21],"skill":[22,82,115],"gaps":[23],"of":[24,45,52,74,97],"LLMs":[25],"and":[26,71,108,113],"how":[27],"improve":[29],"them.To":[30],"make":[31],"these":[32],"weaknesses":[33],"visible,":[34],"we":[35],"propose":[36],"Scaffolded":[37],"Task":[38],"Design":[39],"(STaD)":[40],"framework.STaD":[41],"generates":[42],"controlled":[43],"variations":[44],"tasks":[47],"based":[48],"on":[49,94],"the":[50,79,86],"concept":[51],"scaffolding,":[53],"which":[54],"introduces":[55],"structured,":[56],"incremental":[57],"support":[58],"step-by-step":[61],"manner.Rather":[62],"than":[63],"inspecting":[64],"failures":[65],"individually,":[66],"this":[67],"approach":[68],"enables":[69],"systematic":[70],"scalable":[72],"probing":[73],"model":[75],"behavior":[76],"by":[77],"identifying":[78],"specific":[80],"reasoning":[81,106],"compositions":[83],"they":[84],"lack.Treating":[85],"black":[90],"box,":[91],"our":[92],"experiments":[93],"six":[95],"models":[96],"varying":[98],"sizes":[99],"reveal":[100],"multiple":[101],"failure":[102],"points":[103],"three":[105],"benchmarks":[107],"highlight":[109],"each":[110],"model's":[111],"unique":[112],"distinct":[114],"gaps.":[116]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
