{"id":"https://openalex.org/W6929494239","doi":"https://doi.org/10.18653/2026.emnlp-main.149","title":"From Test-taking to Cognitive Scaffolding: A Pedagogical Diagnostic Benchmark for LLMs on English Standardized Tests","display_name":"From Test-taking to Cognitive Scaffolding: A Pedagogical Diagnostic Benchmark for LLMs on English Standardized Tests","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W6929494239","doi":"https://doi.org/10.18653/2026.emnlp-main.149"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.149","doi":"https://doi.org/10.18653/2026.emnlp-main.149","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.149","pdf_url":"https://aclanthology.org/2026.emnlp-main.149.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.emnlp-main.149.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122928147","display_name":"Luoxi Tang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luoxi Tang","raw_affiliation_strings":["Binghamton University , 2 BlossomsAI ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Binghamton University , 2 BlossomsAI ,","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143181502","display_name":"Tharunya Sundar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tharunya Sundar","raw_affiliation_strings":["Binghamton University , 2 BlossomsAI ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Binghamton University , 2 BlossomsAI ,","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005332727","display_name":"\u5b5f\u5b87\u6865","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuqiao Meng","raw_affiliation_strings":["Binghamton University , 2 BlossomsAI ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Binghamton University , 2 BlossomsAI ,","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuai Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuai Yang","raw_affiliation_strings":["Binghamton University , 2 BlossomsAI ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Binghamton University , 2 BlossomsAI ,","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143172137","display_name":"Ankita Patra","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankita Patra","raw_affiliation_strings":["Binghamton University , 2 BlossomsAI ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Binghamton University , 2 BlossomsAI ,","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143231671","display_name":"Lakshmi Manohar Chippada","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lakshmi Manohar Chippada","raw_affiliation_strings":["Binghamton University , 2 BlossomsAI ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Binghamton University , 2 BlossomsAI ,","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128504066","display_name":"J M Zhao","orcid":"https://orcid.org/0000-0001-7304-0255","observed_orcids":["https://orcid.org/0000-0001-7304-0255"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiqian Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143203917","display_name":"Yi Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043402333","display_name":"Weicheng Ma","orcid":"https://orcid.org/0000-0001-7494-9874","observed_orcids":["https://orcid.org/0000-0001-7494-9874"]},"institutions":[{"id":"https://openalex.org/I177721651","display_name":"Oakland University","ror":"https://ror.org/01ythxj32","country_code":"US","type":"education","lineage":["https://openalex.org/I177721651"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weicheng Ma","raw_affiliation_strings":["Oakland University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oakland University","institution_ids":["https://openalex.org/I177721651"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zhaohan Xi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaohan Xi","raw_affiliation_strings":["Binghamton University , 2 BlossomsAI ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Binghamton University , 2 BlossomsAI ,","institution_ids":["https://openalex.org/I123946342"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.6106,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93283449,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3433","last_page":"3470"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9106000065803528,"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":0.9106000065803528,"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/T14414","display_name":"Artificial Intelligence in Education","score":0.06960000097751617,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.004800000227987766,"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/large-language-models","display_name":"large language models","score":0.8999999761581421},{"id":"https://openalex.org/keywords/cognitive-scaffolding","display_name":"cognitive scaffolding","score":0.8560000061988831},{"id":"https://openalex.org/keywords/ai-tutoring","display_name":"AI tutoring","score":0.6899999976158142},{"id":"https://openalex.org/keywords/reasoning-paths","display_name":"reasoning paths","score":0.5630000233650208},{"id":"https://openalex.org/keywords/misconceptions","display_name":"misconceptions","score":0.6639999747276306},{"id":"https://openalex.org/keywords/multimodal-benchmark","display_name":"multimodal benchmark","score":0.7730000019073486},{"id":"https://openalex.org/keywords/test-taking-strategies","display_name":"test-taking strategies","score":0.6019999980926514}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8012999892234802},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6536999940872192},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5942999720573425},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.538100004196167},{"id":"https://openalex.org/C203151758","wikidata":"https://www.wikidata.org/wiki/Q3244907","display_name":"Standardized test","level":2,"score":0.5027999877929688},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4814999997615814},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.47049999237060547},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4465000033378601},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4235000014305115},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.37720000743865967},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33250001072883606},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3303000032901764},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.31929999589920044},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.31130000948905945},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.29159998893737793},{"id":"https://openalex.org/C188231857","wikidata":"https://www.wikidata.org/wiki/Q2585724","display_name":"Educational assessment","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.25459998846054077}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.emnlp-main.149","doi":"https://doi.org/10.18653/2026.emnlp-main.149","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.149","pdf_url":"https://aclanthology.org/2026.emnlp-main.149.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.17056","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.17056","pdf_url":"https://arxiv.org/pdf/2505.17056","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.17056","doi":"https://doi.org/10.48550/arxiv.2505.17056","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.17056","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.emnlp-main.149","doi":"https://doi.org/10.18653/2026.emnlp-main.149","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.149","pdf_url":"https://aclanthology.org/2026.emnlp-main.149.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.8278999924659729}],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.8670690059661865}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6929494239.pdf","grobid_xml":"https://content.openalex.org/works/W6929494239.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7127412944","https://openalex.org/W7166810847","https://openalex.org/W7126181858","https://openalex.org/W4417230097","https://openalex.org/W7155048810","https://openalex.org/W4405355289","https://openalex.org/W6929772059","https://openalex.org/W7165796162","https://openalex.org/W4409360946","https://openalex.org/W4415981784"],"abstract_inverted_index":{"As":[0],"large":[1],"language":[2],"models":[3,48],"(LLMs)":[4],"are":[5,128],"increasingly":[6],"integrated":[7],"into":[8],"educational":[9],"tools,":[10],"current":[11],"evaluations":[12],"on":[13,18,61,118],"standardized":[14],"tests":[15],"predominantly":[16],"focus":[17],"binary":[19],"outcome":[20],"accuracy.Instead,":[21],"an":[22],"effective":[23],"AI":[24],"tutor":[25],"must":[26],"exhibit":[27],"faithful":[28],"reasoning,":[29],"elucidate":[30],"solution":[31],"strategies,":[32],"and":[33,73,95,113],"diagnose":[34],"specific":[35,100],"human":[36],"misconceptions.To":[37],"bridge":[38],"this":[39,62],"gap,":[40],"we":[41,64,105],"introduce":[42],"a":[43,55,58,67,131,139,143,205,290,295],"pedagogical":[44],"diagnostic":[45],"framework":[46],"that":[47,98,107,114,123],"English":[49],"Standardized":[50],"Test":[51],"(EST)":[52],"problem-solving":[53],"as":[54],"traversal":[56],"through":[57],"cognitive":[59,101],"framework.Based":[60],"framework,":[63],"present":[65],"ESTBOOK,":[66],"multimodal":[68],"benchmark":[69],"encompassing":[70],"10,576":[71],"questions":[72,90],"29":[74],"task":[75],"types":[76],"across":[77],"five":[78],"major":[79],"exams.Unlike":[80],"traditional":[81],"datasets,":[82],"EST-BOOK":[83],"goes":[84],"beyond":[85],"data":[86],"aggregation":[87],"by":[88],"enriching":[89],"with":[91],"formalized":[92],"reasoning":[93,111],"trajectories":[94],"distractor":[96],"rationales":[97],"capture":[99],"traps.Through":[102],"extensive":[103],"evaluations,":[104],"show":[106],"ESTBOOK":[108],"identifies":[109],"fine-grained":[110],"bottlenecks":[112],"lightweight":[115],"mitigation":[116],"based":[117],"these":[119],"diagnoses":[120],"provides":[121],"evidence":[122],"the":[124],"identified":[125],"failure":[126],"modes":[127],"actionable.<":[129],"l":[130,214],"t":[132,136,170,173,202,261,264,284,303],"e":[133,145,153,201],"x":[134,208,248],"i":[135,186,222,251],"s":[137,144,150,223,292],"h":[138,239],"1":[140,204,254],"_":[141],"b":[142,164,188,233,260,274],"6":[146,184],"4":[147,176,199,211,306],"=":[148,177],"\"":[149,178],"/":[151,174,246,298],"D":[152,225,228,255],"Z":[154,167],"I":[155,215,218],"p":[156,310],"o":[157,213,262],"j":[158,282],"8":[159,193],"3":[160,185,198,232,256,259],"w":[161,166,258,268,305],"g":[162,227,247],"J":[163,197,210],"q":[165],"M":[168,250],"k":[169],"B":[171,183,190,267,276],"7":[172,285,300,302],"z":[175,231,237,309],">":[179],"A":[180,181,182,195],"c":[187,263],"V":[189,293,304],"N":[191,194],"S":[192,209,217],"E":[196],"W":[200,229,230,273],"X":[203,207,221,252,266],"O":[206,242,269,270,286,301,307],"K":[212,296],"9":[216,271],"U":[219],"v":[220,253,257,299],"Y":[224,249],"+":[226,291],"R":[234],"L":[235,245],"d":[236,238,240],"y":[241,287],"G":[243,272],"0":[244],"P":[265],"m":[275,297],"T":[277],"F":[278],"n":[279,294],"2":[280,308],"r":[281,289],"u":[283,288]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2025-10-10T00:00:00"}