{"id":"https://openalex.org/W7128786722","doi":"https://doi.org/10.1145/3770761.3777333","title":"CSTutorBench: Benchmarking Large Language Models for Realistic Computer Science Tutoring","display_name":"CSTutorBench: Benchmarking Large Language Models for Realistic Computer Science Tutoring","publication_year":2026,"publication_date":"2026-02-13","ids":{"openalex":"https://openalex.org/W7128786722","doi":"https://doi.org/10.1145/3770761.3777333"},"language":null,"primary_location":{"id":"doi:10.1145/3770761.3777333","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770761.3777333","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th ACM Technical Symposium on Computer Science Education V.2","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3770761.3777333","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125914939","display_name":"Zekai Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zekai Cheng","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0009-0009-4796-3385","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111232262","display_name":"Yunfeng Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yunfeng Wan","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0009-0005-5189-9444","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125950199","display_name":"Daijiao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Daijiao Liu","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0009-0002-8700-6642","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125896115","display_name":"Yuekang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yuekang Li","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-4382-0757","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125042145","display_name":"Yuchao Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yuchao Jiang","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-2031-4712","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125908427","display_name":"Dong Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dong Gong","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2668-9630","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1263","last_page":"1264"},"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":0.765999972820282,"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":0.765999972820282,"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/T10636","display_name":"Innovative Teaching and Learning Methods","score":0.026900000870227814,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational 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/T10028","display_name":"Topic Modeling","score":0.022600000724196434,"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/benchmarking","display_name":"Benchmarking","score":0.8043000102043152},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6509000062942505},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.6305000185966492},{"id":"https://openalex.org/keywords/gauge","display_name":"Gauge (firearms)","score":0.40119999647140503},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3549000024795532},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.3091000020503998}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8043000102043152},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577000260353088},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6509000062942505},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.6305000185966492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46209999918937683},{"id":"https://openalex.org/C40976572","wikidata":"https://www.wikidata.org/wiki/Q2330873","display_name":"Gauge (firearms)","level":2,"score":0.40119999647140503},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3714999854564667},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3379000127315521},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33160001039505005},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32089999318122864},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3770761.3777333","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770761.3777333","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th ACM Technical Symposium on Computer Science Education V.2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3770761.3777333","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770761.3777333","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th ACM Technical Symposium on Computer Science Education V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8346567749977112}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W4389518941","https://openalex.org/W4402670041"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"show":[4],"promise":[5],"for":[6],"CS":[7,90],"educational":[8],"assistance;":[9],"however,":[10],"the":[11,62],"absence":[12],"of":[13,64,102],"comprehensive":[14],"benchmarks":[15],"limits":[16],"our":[17],"ability":[18],"to":[19],"assess":[20],"their":[21],"effectiveness":[22],"in":[23,67,100],"real-world":[24],"teaching":[25],"scenarios":[26],"accurately.":[27],"To":[28],"fill":[29],"this":[30],"gap,":[31],"we":[32,48,93],"present":[33],"CSTutorBench,":[34],"a":[35],"dataset":[36],"from":[37],"authentic":[38],"course":[39],"discussion":[40],"forums":[41],"with":[42],"2,970":[43],"multimodal":[44],"question\u2013answer":[45],"pairs.":[46],"Additionally,":[47],"propose":[49],"an":[50],"evaluation":[51],"framework":[52],"across":[53],"five":[54],"dimensions\u2014accuracy,":[55],"clarity,":[56,105],"conciseness,":[57],"personalization,":[58],"and":[59,78,83,104,112],"engagement\u2014to":[60],"gauge":[61],"performance":[63,99],"various":[65],"models":[66],"tutoring":[68,91],"settings.":[69],"We":[70],"benchmark":[71],"leading":[72,95],"LLMs\u2014including":[73],"GPT-4o,":[74],"Claude,":[75],"Llama":[76],"4,":[77],"others\u2014using":[79],"both":[80],"automated":[81],"metrics":[82],"expert":[84],"human":[85,98],"assessments.":[86],"Across":[87],"these":[88],"real":[89],"exchanges,":[92],"found":[94],"LLMs":[96],"approach":[97],"terms":[101],"accuracy":[103],"but":[106],"fall":[107],"notably":[108],"short":[109],"on":[110],"personalization":[111],"interactive":[113],"scaffolding,":[114],"often":[115],"producing":[116],"fluent":[117],"yet":[118],"less":[119],"learner-adaptive":[120],"guidance.":[121]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-14T00:00:00"}