{"id":"https://openalex.org/W4407122905","doi":"https://doi.org/10.48550/arxiv.2502.00016","title":"Large Language Models for Education: ChemTAsk -- An Open-Source Paradigm for Automated Q&A in the Graduate Classroom","display_name":"Large Language Models for Education: ChemTAsk -- An Open-Source Paradigm for Automated Q&A in the Graduate Classroom","publication_year":2025,"publication_date":"2025-01-10","ids":{"openalex":"https://openalex.org/W4407122905","doi":"https://doi.org/10.48550/arxiv.2502.00016"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2502.00016","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.00016","pdf_url":"https://arxiv.org/pdf/2502.00016","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.00016","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023612814","display_name":"Ryann M. Perez","orcid":"https://orcid.org/0000-0003-2233-8910","observed_orcids":["https://orcid.org/0000-0003-2233-8910"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Perez, Ryann M.","raw_affiliation_strings":["Department of Chemistry , University of Pennsylvania , Philadelphia , Pennsylvania 19104 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry , University of Pennsylvania , Philadelphia , Pennsylvania 19104 , USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001939171","display_name":"Marie Shimogawa","orcid":"https://orcid.org/0000-0002-8471-9375","observed_orcids":["https://orcid.org/0000-0002-8471-9375"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shimogawa, Marie","raw_affiliation_strings":["Department of Chemistry , University of Pennsylvania , Philadelphia , Pennsylvania 19104 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry , University of Pennsylvania , Philadelphia , Pennsylvania 19104 , USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chang, Yanan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chang, Yanan","raw_affiliation_strings":["Department of Chemistry , University of Pennsylvania , Philadelphia , Pennsylvania 19104 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry , University of Pennsylvania , Philadelphia , Pennsylvania 19104 , USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011247369","display_name":"Hoang Anh T. Phan","orcid":"https://orcid.org/0000-0001-6488-0404","observed_orcids":["https://orcid.org/0000-0001-6488-0404"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Phan, Hoang Anh T.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096772918","display_name":"Jason G. Marmorstein","orcid":"https://orcid.org/0009-0004-0590-4428","observed_orcids":["https://orcid.org/0009-0004-0590-4428"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marmorstein, Jason G.","raw_affiliation_strings":["Department of Chemistry , University of Pennsylvania , Philadelphia , Pennsylvania 19104 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry , University of Pennsylvania , Philadelphia , Pennsylvania 19104 , USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113376190","display_name":"Evan S. K. Yanagawa","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanagawa, Evan S. K.","raw_affiliation_strings":["Department of Chemistry , University of Pennsylvania , Philadelphia , Pennsylvania 19104 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry , University of Pennsylvania , Philadelphia , Pennsylvania 19104 , USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028662408","display_name":"E. James Petersson","orcid":"https://orcid.org/0000-0003-3854-9210","observed_orcids":["https://orcid.org/0000-0003-3854-9210"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Petersson, E. James","raw_affiliation_strings":["Department of Chemistry , University of Pennsylvania , Philadelphia , Pennsylvania 19104 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry , University of Pennsylvania , Philadelphia , Pennsylvania 19104 , USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"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/T14414","display_name":"Artificial Intelligence in Education","score":0.9326000213623047,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T14414","display_name":"Artificial Intelligence in Education","score":0.9326000213623047,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.051100000739097595,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.006899999920278788,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"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/large-language-models","display_name":"large language models","score":0.9330000281333923},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.968999981880188},{"id":"https://openalex.org/keywords/automatic-question-answering","display_name":"automatic question answering","score":0.843999981880188},{"id":"https://openalex.org/keywords/graduate-education","display_name":"graduate education","score":0.7820000052452087},{"id":"https://openalex.org/keywords/teaching-assistants","display_name":"teaching assistants","score":0.6060000061988831},{"id":"https://openalex.org/keywords/confabulation","display_name":"confabulation","score":0.8190000057220459},{"id":"https://openalex.org/keywords/student-feedback","display_name":"student feedback","score":0.6359999775886536},{"id":"https://openalex.org/keywords/self-assessment","display_name":"self-assessment","score":0.6359999775886536},{"id":"https://openalex.org/keywords/llm-benchmarking","display_name":"LLM benchmarking","score":0.48899999260902405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5936518311500549},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5876278877258301},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.4900702238082886},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.34045714139938354},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25987720489501953},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.1266472339630127}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2502.00016","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.00016","pdf_url":"https://arxiv.org/pdf/2502.00016","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2502.00016","doi":"https://doi.org/10.48550/arxiv.2502.00016","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.00016","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.00016","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.00016","pdf_url":"https://arxiv.org/pdf/2502.00016","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.9901999831199646}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1842713513","display_name":"The Role of Thioamides in Natural and Designed Proteins","funder_award_id":"2203909","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3549828030","display_name":null,"funder_award_id":"NIH T32","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G9000874752","display_name":"Predoctoral Training at the Chemistry-Biology Interface","funder_award_id":"T32GM133398","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320334128","display_name":"Vagelos Institute for Energy Science and Technology, University of Pennsylvania","ror":null},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320337393","display_name":"Division of Chemistry","ror":"https://ror.org/01ar8dr59"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407122905.pdf","grobid_xml":"https://content.openalex.org/works/W4407122905.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W4285429195","https://openalex.org/W4396958517","https://openalex.org/W4401306886","https://openalex.org/W4401518309","https://openalex.org/W4401947350","https://openalex.org/W4402773236","https://openalex.org/W4402827393","https://openalex.org/W4404764563","https://openalex.org/W4404782878"],"related_works":["https://openalex.org/W7124147697","https://openalex.org/W4402480699","https://openalex.org/W4406036407","https://openalex.org/W7139014777","https://openalex.org/W7125599262","https://openalex.org/W4381377104","https://openalex.org/W7166536747","https://openalex.org/W4407685288","https://openalex.org/W4408855896","https://openalex.org/W4404317098"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,149,173],"(LLMs)":[3],"show":[4],"promise":[5],"for":[6,77,163,189,211],"aiding":[7],"graduate":[8],"level":[9],"education,":[10],"but":[11],"are":[12],"limited":[13],"by":[14],"their":[15,120,124],"training":[16],"data":[17],"and":[18,46,103,122,142,147,152,183,213],"potential":[19,190,197],"confabulations.":[20,191],"We":[21],"developed":[22],"ChemTAsk,":[23],"an":[24,60,158],"open-source":[25],"pipeline":[26],"that":[27,135,171],"combines":[28],"LLMs":[29,200],"with":[30,94,201],"retrieval-augmented":[31],"generation":[32],"(RAG)":[33],"to":[34,49,53,74,83,126,177,187,203],"provide":[35],"accurate,":[36],"context-specific":[37],"assistance.":[38],"ChemTAsk":[39,76,90,136,194],"utilizes":[40],"course":[41,64],"materials,":[42],"including":[43],"lecture":[44],"transcripts":[45],"primary":[47],"publications,":[48],"generate":[50],"accurate":[51,105],"responses":[52,121],"student":[54,101],"queries.":[55],"Over":[56],"nine":[57],"weeks":[58],"in":[59,73,79,99,109,119,179,185],"advanced":[61],"biological":[62,160],"chemistry":[63,161],"at":[65],"the":[66,127,130,180,196],"University":[67],"of":[68,129,166,198],"Pennsylvania,":[69],"students":[70,212],"could":[71],"opt":[72],"use":[75],"assistance":[78,125],"any":[80],"assignment":[81],"or":[82],"understand":[84],"class":[85],"material.":[86],"Comparative":[87],"analysis":[88],"showed":[89],"performed":[91],"on":[92,157],"par":[93],"human":[95],"teaching":[96],"assistants":[97],"(TAs)":[98],"understanding":[100],"queries":[102],"providing":[104],"information,":[106],"particularly":[107],"excelling":[108],"creative":[110],"problem-solving":[111],"tasks.":[112],"In":[113],"contrast,":[114],"TAs":[115],"were":[116,155,174],"more":[117,175],"precise":[118],"tailored":[123],"specifics":[128],"class.":[131],"Student":[132],"feedback":[133],"indicated":[134],"was":[137,169],"perceived":[138],"as":[139],"correct,":[140],"helpful,":[141],"faster":[143],"than":[144],"TAs.":[145],"Open-source":[146],"proprietary":[148],"from":[150],"Meta":[151],"OpenAI":[153,172],"respectively":[154],"tested":[156],"original":[159],"benchmark":[162],"future":[164],"iterations":[165],"ChemTAsk.":[167],"It":[168],"found":[170],"tolerant":[176],"deviations":[178],"input":[181],"prompt":[182],"excelled":[184],"self-assessment":[186],"safeguard":[188],"Taken":[192],"together,":[193],"demonstrates":[195],"integrating":[199],"RAG":[202],"enhance":[204],"educational":[205],"support,":[206],"offering":[207],"a":[208],"scalable":[209],"tool":[210],"educators.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-02-05T00:00:00"}
