{"id":"https://openalex.org/W7165533749","doi":"https://doi.org/10.1145/3774398.3811588","title":"Uncertainty-Guided Sampling for LLM Calibration in Automated Short Answer Grading","display_name":"Uncertainty-Guided Sampling for LLM Calibration in Automated Short Answer Grading","publication_year":2026,"publication_date":"2026-06-22","ids":{"openalex":"https://openalex.org/W7165533749","doi":"https://doi.org/10.1145/3774398.3811588"},"language":null,"primary_location":{"id":"doi:10.1145/3774398.3811588","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774398.3811588","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 Thirteenth ACM Conference on Learning @ Scale","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774398.3811588","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134846924","display_name":"Ovide KUICHUA","orcid":null},"institutions":[{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ovide Kuichua","raw_affiliation_strings":["Polytechnique Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada"],"raw_orcid":"https://orcid.org/0009-0001-5099-3958","affiliations":[{"raw_affiliation_string":"Polytechnique Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada","institution_ids":["https://openalex.org/I45683168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005514400","display_name":"Michel C. Desmarais","orcid":"https://orcid.org/0000-0002-2990-1078"},"institutions":[{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Michel Desmarais","raw_affiliation_strings":["Polytechnique Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada"],"raw_orcid":"https://orcid.org/0000-0002-2990-1078","affiliations":[{"raw_affiliation_string":"Polytechnique Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada","institution_ids":["https://openalex.org/I45683168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137595488","display_name":"Arman Bakhtiari","orcid":"https://orcid.org/0009-0000-7828-7708"},"institutions":[{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Arman Bakhtiari","raw_affiliation_strings":["Polytechnique Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada"],"raw_orcid":"https://orcid.org/0009-0000-7828-7708","affiliations":[{"raw_affiliation_string":"Polytechnique Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada","institution_ids":["https://openalex.org/I45683168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032479034","display_name":"Chah\u00e9 Nerguizian","orcid":"https://orcid.org/0000-0002-4971-5723"},"institutions":[{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Chah\u00e9 Nerguizian","raw_affiliation_strings":["Polytechnique Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada"],"raw_orcid":"https://orcid.org/0000-0002-4971-5723","affiliations":[{"raw_affiliation_string":"Polytechnique Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada","institution_ids":["https://openalex.org/I45683168"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029637555","display_name":"Alexandre G\u00e9linas","orcid":null},"institutions":[{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Alexandre G\u00e9linas","raw_affiliation_strings":["Polytechnique Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada"],"raw_orcid":"https://orcid.org/0009-0007-0925-4188","affiliations":[{"raw_affiliation_string":"Polytechnique Montr\u00e9al, Montr\u00e9al, Qu\u00e9bec, Canada","institution_ids":["https://openalex.org/I45683168"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45683168"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80129067,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"443","last_page":"447"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.23190000653266907,"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/T10028","display_name":"Topic Modeling","score":0.23190000653266907,"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/T13309","display_name":"Reliability and Agreement in Measurement","score":0.042399998754262924,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11894","display_name":"Radiology practices and education","score":0.02539999969303608,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.5637999773025513},{"id":"https://openalex.org/keywords/grading","display_name":"Grading (engineering)","score":0.45080000162124634},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.40619999170303345},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.37299999594688416},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.27639999985694885}],"concepts":[{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.5637999773025513},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5296000242233276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5026999711990356},{"id":"https://openalex.org/C2777286243","wikidata":"https://www.wikidata.org/wiki/Q5591926","display_name":"Grading (engineering)","level":2,"score":0.45080000162124634},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.40619999170303345},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3671000003814697},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2964000105857849},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774398.3811588","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774398.3811588","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 Thirteenth ACM Conference on Learning @ Scale","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774398.3811588","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774398.3811588","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 Thirteenth ACM Conference on Learning @ Scale","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1971713783","https://openalex.org/W2052929314","https://openalex.org/W2914823529","https://openalex.org/W3124893573","https://openalex.org/W3192880933","https://openalex.org/W4285223017","https://openalex.org/W4293094054","https://openalex.org/W4323338676","https://openalex.org/W4391254711","https://openalex.org/W4407841980","https://openalex.org/W4410191165","https://openalex.org/W4412874033"],"related_works":[],"abstract_inverted_index":{"Automated":[0],"short":[1],"answer":[2],"grading":[3],"using":[4],"LLMs":[5],"requires":[6],"per-question":[7],"calibration":[8],"with":[9,15,40,91],"human-graded":[10],"examples":[11],"to":[12,35,43,60],"align":[13],"outputs":[14],"instructor":[16,61],"standards.":[17],"Existing":[18],"approaches":[19],"treat":[20],"all":[21],"responses":[22,45],"as":[23],"equally":[24],"informative":[25],"for":[26,139],"calibration.":[27],"We":[28],"propose":[29],"uncertainty-guided":[30],"sampling":[31,90],"that":[32,127],"combines":[33],"stratification":[34],"ensure":[36],"score":[37],"range":[38],"coverage":[39],"uncertainty-based":[41],"selection":[42],"target":[44],"where":[46],"human":[47],"judgment":[48],"is":[49],"most":[50],"informative.":[51],"Using":[52],"Gaussian":[53],"kernel":[54],"regression,":[55],"we":[56],"map":[57],"LLM":[58,128],"scores":[59],"preferences":[62],"from":[63],"these":[64],"selected":[65],"samples.":[66,103],"Evaluated":[67],"on":[68,110,121],"Mohler":[69],"benchmark":[70],"and":[71,113],"PT\\_ASAG":[72],"dataset,":[73],"our":[74],"method":[75],"achieves":[76],"30%":[77],"RMSE":[78],"improvement":[79],"over":[80],"state-of-the-art":[81],"(0.501":[82],"vs":[83],"0.717,":[84],"m=15)":[85],"in":[86],"single-cohort":[87],"deployment.":[88],"Uncertainty":[89],"m=10":[92],"(0.582":[93],"RMSE)":[94],"matches":[95],"rank-based":[96],"at":[97],"m=15":[98],"(0.596),":[99],"requiring":[100],"33%":[101],"fewer":[102],"However,":[104],"cross-validation":[105],"reveals":[106],"this":[107],"advantage":[108],"diminishes":[109],"unseen":[111],"answers,":[112],"per-class":[114],"analysis":[115],"shows":[116],"density":[117],"bias":[118],"limits":[119],"performance":[120],"minority":[122],"grades.":[123],"Our":[124],"findings":[125],"suggest":[126],"uncertainty":[129],"enables":[130],"sample-efficient,":[131],"instructor-centered":[132],"calibration,":[133],"though":[134],"density-aware":[135],"strategies":[136],"are":[137],"needed":[138],"imbalanced":[140],"distributions.":[141]},"counts_by_year":[],"updated_date":"2026-06-24T06:17:17.354583","created_date":"2026-06-23T00:00:00"}