{"id":"https://openalex.org/W7162763970","doi":"https://doi.org/10.48550/arxiv.2605.29274","title":"Learnable Assessment Skills for LLM-based Automated Scoring: Rubric Construction via Iterative Optimization","display_name":"Learnable Assessment Skills for LLM-based Automated Scoring: Rubric Construction via Iterative Optimization","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7162763970","doi":"https://doi.org/10.48550/arxiv.2605.29274"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.29274","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29274","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,"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.2605.29274","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137380359","display_name":"Yun Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137388344","display_name":"Xin Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137345167","display_name":"Xuansheng Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Xuansheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137329673","display_name":"Xiaoming Zhai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhai, Xiaoming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137327820","display_name":"Ninghao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Ninghao","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/T10028","display_name":"Topic Modeling","score":0.24089999496936798,"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":0.24089999496936798,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.15060000121593475,"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/T10467","display_name":"Psychometric Methodologies and Testing","score":0.07970000058412552,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/rubric","display_name":"Rubric","score":0.9050999879837036},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7789999842643738},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6482999920845032},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.4763000011444092},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.4189999997615814},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.32510000467300415}],"concepts":[{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.9050999879837036},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7789999842643738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6568999886512756},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6482999920845032},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.501800000667572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49230000376701355},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.4763000011444092},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25529998540878296},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25189998745918274},{"id":"https://openalex.org/C83282275","wikidata":"https://www.wikidata.org/wiki/Q7435350","display_name":"Scoring algorithm","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.29274","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29274","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,"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.2605.29274","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29274","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,"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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8434808254241943}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"LLM-based":[0,124],"automated":[1],"scoring":[2,47,70,104,125],"approaches":[3],"near-human":[4],"performance,":[5],"but":[6],"scaling":[7],"to":[8],"new":[9],"tasks":[10],"remains":[11],"bottlenecked":[12],"by":[13],"the":[14,53,69,98,129],"per-item":[15],"human":[16],"configuration":[17],"of":[18,55,68,103],"upstream":[19],"stages":[20,67],"such":[21],"as":[22,52,76],"rubric":[23,74],"construction.":[24],"Human":[25],"experts":[26],"bypass":[27],"this":[28,51],"bottleneck":[29],"through":[30,65,100],"evaluation":[31],"heuristics":[32,44],"developed":[33],"over":[34],"extensive":[35],"practice.":[36],"We":[37],"ask":[38],"whether":[39],"LLMs":[40,64],"can":[41],"learn":[42],"similar":[43],"directly":[45],"from":[46],"experience,":[48],"and":[49,93,106,126,144],"formalize":[50],"concept":[54],"assessment":[56],"skills:":[57],"item-independent":[58],"natural-language":[59],"procedural":[60],"knowledge":[61],"that":[62,85,138],"guides":[63],"specific":[66],"workflow.":[71],"Focusing":[72],"on":[73],"construction":[75],"a":[77,87,90],"first":[78],"instantiation,":[79],"we":[80],"propose":[81],"an":[82],"iterative":[83],"framework":[84,110],"decomposes":[86],"skill":[88],"into":[89],"fixed":[91],"scaffold":[92],"learnable":[94],"item-agnostic":[95],"rules,":[96],"refining":[97],"rules":[99],"LLM-driven":[101],"diagnosis":[102],"errors":[105],"validation-gated":[107],"selection.":[108],"The":[109],"requires":[111],"no":[112],"expert-written":[113],"rubric.":[114,132],"On":[115],"all":[116],"ten":[117],"ASAP-SAS":[118],"items,":[119],"optimized":[120],"skills":[121,140],"substantially":[122],"improve":[123],"frequently":[127],"surpass":[128],"dataset-provided":[130],"expert":[131],"Cross-item":[133],"transfer":[134],"experiments":[135],"further":[136],"reveal":[137],"learned":[139],"capture":[141],"both":[142],"generalizable":[143],"item-specific":[145],"patterns.":[146]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-30T00:00:00"}