{"id":"https://openalex.org/W7133310457","doi":"https://doi.org/10.48550/arxiv.2603.00465","title":"Optimizing In-Context Demonstrations for LLM-based Automated Grading","display_name":"Optimizing In-Context Demonstrations for LLM-based Automated Grading","publication_year":2026,"publication_date":"2026-02-28","ids":{"openalex":"https://openalex.org/W7133310457","doi":"https://doi.org/10.48550/arxiv.2603.00465"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.00465","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00465","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.00465","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128009080","display_name":"Yucheng Chu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chu, Yucheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127922707","display_name":"Hang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Hang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127914113","display_name":"Kaiqi Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Kaiqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114452226","display_name":"Yasemin Copur-Gencturk","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Copur-Gencturk, Yasemin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076148574","display_name":"Kevin C. Haudek","orcid":"https://orcid.org/0000-0003-1422-6038"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haudek, Kevin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128025208","display_name":"Joseph Krajcik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krajcik, Joseph","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127972342","display_name":"Jiliang Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Jiliang","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.6168000102043152,"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":0.6168000102043152,"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/T10028","display_name":"Topic Modeling","score":0.07829999923706055,"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/T11122","display_name":"Online Learning and Analytics","score":0.02969999983906746,"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/rubric","display_name":"Rubric","score":0.7867000102996826},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6639000177383423},{"id":"https://openalex.org/keywords/grading","display_name":"Grading (engineering)","score":0.6340000033378601},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5268999934196472},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.46790000796318054},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4625000059604645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7947999835014343},{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.7867000102996826},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6639000177383423},{"id":"https://openalex.org/C2777286243","wikidata":"https://www.wikidata.org/wiki/Q5591926","display_name":"Grading (engineering)","level":2,"score":0.6340000033378601},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5268999934196472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5167999863624573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48399999737739563},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.46790000796318054},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4625000059604645},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37040001153945923},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.298799991607666},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25850000977516174}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.00465","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00465","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.00465","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00465","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.7023229598999023,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automated":[0],"assessment":[1,213],"of":[2,39,45,120,160,191],"open-ended":[3],"student":[4],"responses":[5],"is":[6,33],"a":[7,83,98,110,117,151,154],"critical":[8],"capability":[9],"for":[10,67,210],"scaling":[11],"personalized":[12],"feedback":[13],"in":[14,24,106,167],"education.":[15],"While":[16],"large":[17],"language":[18],"models":[19,80],"(LLMs)":[20],"have":[21],"shown":[22],"promise":[23],"grading":[25,108],"tasks":[26],"via":[27],"in-context":[28],"learning":[29],"(ICL),":[30],"their":[31],"reliability":[32],"heavily":[34],"dependent":[35],"on":[36,55,116,187,199],"the":[37,43,73,158,184,188,208],"selection":[38,103,121],"few-shot":[40],"exemplars":[41,142],"and":[42,104,122,170,202],"construction":[44],"high-quality":[46],"rationales.":[47],"Standard":[48],"retrieval":[49,180],"methods":[50],"typically":[51],"select":[52],"examples":[53],"based":[54],"semantic":[56],"similarity,":[57],"which":[58],"often":[59],"fails":[60],"to":[61,77,128,157],"capture":[62],"subtle":[63],"decision":[64],"boundaries":[65],"required":[66],"rubric":[68,204],"adherence.":[69,205],"Furthermore,":[70],"manually":[71],"crafting":[72],"expert":[74],"rationales":[75,146],"needed":[76],"guide":[78],"these":[79,88],"can":[81],"be":[82],"significant":[84],"bottleneck.":[85],"To":[86],"address":[87],"limitations,":[89],"we":[90],"introduce":[91],"GUIDE":[92,114,176,206],"(Grading":[93],"Using":[94],"Iteratively":[95],"Designed":[96],"Exemplars),":[97],"framework":[99],"that":[100,132,147,175,215],"reframes":[101],"exemplar":[102],"refinement":[105],"automated":[107],"as":[109],"boundary-focused":[111],"optimization":[112],"problem.":[113],"operates":[115],"continuous":[118],"loop":[119],"refinement,":[123],"employing":[124],"novel":[125],"contrastive":[126],"operators":[127],"identify":[129],"\"boundary":[130],"pairs\"":[131],"are":[133],"semantically":[134],"similar":[135],"but":[136],"possess":[137],"different":[138],"grades.":[139,162],"We":[140],"enhance":[141],"by":[143],"generating":[144],"discriminative":[145],"explicitly":[148],"articulate":[149],"why":[150],"response":[152],"receives":[153],"specific":[155],"score":[156],"exclusion":[159],"adjacent":[161],"Extensive":[163],"experiments":[164],"across":[165],"datasets":[166],"physics,":[168],"chemistry,":[169],"pedagogical":[171,220],"content":[172],"knowledge":[173],"demonstrate":[174],"significantly":[177],"outperforms":[178],"standard":[179],"baselines.":[181],"By":[182],"focusing":[183],"model's":[185],"attention":[186],"precise":[189],"edges":[190],"rubric,":[192],"our":[193],"approach":[194],"shows":[195],"exceptionally":[196],"robust":[197],"gains":[198],"borderline":[200],"cases":[201],"improved":[203],"paves":[207],"way":[209],"trusted,":[211],"scalable":[212],"systems":[214],"align":[216],"closely":[217],"with":[218],"human":[219],"standards.":[221]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-04T00:00:00"}