{"id":"https://openalex.org/W4409194885","doi":"https://doi.org/10.5220/0013291700003932","title":"Evaluating the Potential of LLMs for Better Short Answer Scoring","display_name":"Evaluating the Potential of LLMs for Better Short Answer Scoring","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409194885","doi":"https://doi.org/10.5220/0013291700003932"},"language":"en","primary_location":{"id":"doi:10.5220/0013291700003932","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013291700003932","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Computer Supported Education","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0013291700003932","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116971515","display_name":"Aleksandar Todorov","orcid":null},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Aleksandar Todorov","raw_affiliation_strings":["Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116971516","display_name":"Elisa Klunder","orcid":null},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Elisa Klunder","raw_affiliation_strings":["Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5116971517","display_name":"Julia Belloni","orcid":null},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Julia Belloni","raw_affiliation_strings":["Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5116971515"],"corresponding_institution_ids":["https://openalex.org/I169381384"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03271819,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"108","last_page":"119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9571999907493591,"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":0.9571999907493591,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9222999811172485,"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/computer-science","display_name":"Computer science","score":0.5607396364212036}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5607396364212036}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5220/0013291700003932","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013291700003932","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Computer Supported Education","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/a1927635-82bb-4783-82bc-41d6813d4708","is_oa":false,"landing_page_url":"https://research.rug.nl/en/publications/a1927635-82bb-4783-82bc-41d6813d4708","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Todorov, A, Klunder, E & Belloni, J E 2025, Evaluating the Potential of LLMs for Better Short Answer Scoring. in B du Boulay, T Di Mascio, E Tovar & C Meinel (eds), Proceedings of the 17th International Conference on Computer Supported Education. CSEDU edn, vol. 2, International Conference on Computer Supported Education, CSEDU - Proceedings, vol. 2, Science and Technology Publications, Lda, pp. 108-119, 17th International Conference on Computer Supported Education, CSEDU 2025, Porto, Portugal, 01/04/2025. https://doi.org/10.5220/0013291700003932","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.rug.nl:openaire/a1927635-82bb-4783-82bc-41d6813d4708","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/a1927635-82bb-4783-82bc-41d6813d4708","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Todorov, A, Klunder, E & Belloni, J E 2025, Evaluating the Potential of LLMs for Better Short Answer Scoring. in B du Boulay, T Di Mascio, E Tovar & C Meinel (eds), Proceedings of the 17th International Conference on Computer Supported Education. CSEDU edn, vol. 2, International Conference on Computer Supported Education, CSEDU - Proceedings, vol. 2, Science and Technology Publications, Lda, pp. 108-119, 17th International Conference on Computer Supported Education, CSEDU 2025, Porto, Portugal, 01/04/2025. https://doi.org/10.5220/0013291700003932","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.5220/0013291700003932","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013291700003932","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Computer Supported Education","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Automated":[0],"Short":[1],"Answer":[2],"Grading":[3],"(ASAG)":[4],"has":[5],"emerged":[6],"as":[7,25],"a":[8,61,65,96],"promising":[9],"tool":[10],"for":[11,91],"the":[12,49,75,109,124],"challenge":[13],"of":[14,28,44,51,112],"assessing":[15],"open":[16,30],"student":[17,53],"responses":[18,55],"in":[19,115],"an":[20],"efficient":[21],"and":[22,35,58,64,123],"scalable":[23],"manner":[24],"manual":[26],"grading":[27,52],"such":[29],"short":[31],"answers":[32],"is":[33],"labor-intensive":[34],"time-consuming.":[36],"In":[37,78],"this":[38,79],"study,":[39],"we":[40,81],"present":[41],"several":[42],"ways":[43],"refining":[45],"LLMs":[46,114],"to":[47,70],"fit":[48],"task":[50],"short-answer":[54,92],"robustly,":[56],"fairly,":[57],"consistently,":[59],"including":[60],"task-specific":[62],"approach":[63],"combined":[66],"variant,":[67],"being":[68],"able":[69],"assess":[71],"different":[72,120],"tasks":[73],"within":[74],"same":[76],"model.":[77],"regard,":[80],"explore":[82],"two":[83],"key":[84],"questions:":[85],"(1)":[86],"Are":[87],"transformer-based":[88,98],"models":[89,130],"suitable":[90],"grading?":[93],"(2)":[94],"Can":[95],"single":[97],"model":[99],"effectively":[100],"generalize":[101],"across":[102],"diverse":[103],"tasks?":[104],"The":[105],"experimental":[106,125],"results":[107,126],"showed":[108,127],"significant":[110],"potential":[111],"fine-tuned":[113],"ASAG.":[116],"We":[117],"further":[118],"compared":[119],"fine-tuning":[121,133],"strategies":[122],"that":[128],"full-fine-tuned":[129],"outperformed":[131],"other":[132],"approaches.":[134]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}