{"id":"https://openalex.org/W4415314128","doi":"https://doi.org/10.48550/arxiv.2510.06239","title":"OpenStaxQA: A multilingual dataset based on open-source college textbooks","display_name":"OpenStaxQA: A multilingual dataset based on open-source college textbooks","publication_year":2025,"publication_date":"2025-10-03","ids":{"openalex":"https://openalex.org/W4415314128","doi":"https://doi.org/10.48550/arxiv.2510.06239"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2510.06239","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.06239","pdf_url":"https://arxiv.org/pdf/2510.06239","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.06239","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058904450","display_name":"Pranav Gupta","orcid":"https://orcid.org/0000-0003-2640-1390","observed_orcids":["https://orcid.org/0000-0003-2640-1390"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gupta, Pranav","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5058904450"],"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":0.9179999828338623,"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":0.9179999828338623,"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":0.030799999833106995,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.01510000042617321,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/multilingual-dataset","display_name":"multilingual dataset","score":0.6949999928474426},{"id":"https://openalex.org/keywords/evaluation-benchmark","display_name":"evaluation benchmark","score":0.6729999780654907},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8989999890327454},{"id":"https://openalex.org/keywords/qlora","display_name":"QLoRA","score":0.6539999842643738},{"id":"https://openalex.org/keywords/low-rank-adapters","display_name":"low-rank adapters","score":0.7630000114440918},{"id":"https://openalex.org/keywords/zero-shot-evaluation","display_name":"zero-shot evaluation","score":0.7379999756813049},{"id":"https://openalex.org/keywords/artificial-intelligence-in-education","display_name":"artificial intelligence in education","score":0.3540000021457672},{"id":"https://openalex.org/keywords/spanish-language","display_name":"Spanish language","score":0.32199999690055847},{"id":"https://openalex.org/keywords/polish","display_name":"Polish","score":0.9990000128746033}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7250000238418579},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6287000179290771},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5932999849319458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.453000009059906},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44130000472068787},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4169999957084656},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33640000224113464},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.30309998989105225},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C2778883600","wikidata":"https://www.wikidata.org/wiki/Q2390977","display_name":"Language proficiency","level":2,"score":0.2660999894142151}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2510.06239","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.06239","pdf_url":"https://arxiv.org/pdf/2510.06239","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.06239","doi":"https://doi.org/10.48550/arxiv.2510.06239","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.06239","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:2510.06239","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.06239","pdf_url":"https://arxiv.org/pdf/2510.06239","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":null,"license_id":null,"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":0.6164000034332275}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7138377515","https://openalex.org/W7166804551","https://openalex.org/W7165670298","https://openalex.org/W4400525527","https://openalex.org/W4404310834","https://openalex.org/W4417300318","https://openalex.org/W4407025807","https://openalex.org/W7133217022","https://openalex.org/W7172338067","https://openalex.org/W4393023489"],"abstract_inverted_index":{"We":[0,29,80],"present":[1],"OpenStaxQA,":[2],"an":[3,74],"evaluation":[4,57],"benchmark":[5],"specific":[6],"to":[7,67,73,86],"college-level":[8],"educational":[9],"applications":[10],"based":[11],"on":[12,42,58,77],"43":[13],"open-source":[14],"college":[15],"textbooks":[16],"in":[17,65],"English,":[18],"Spanish,":[19],"and":[20,31],"Polish,":[21],"available":[22],"under":[23],"a":[24,55],"permissive":[25],"Creative":[26],"Commons":[27],"license.":[28],"finetune":[30],"evaluate":[32],"large":[33],"language":[34],"models":[35],"(LLMs)":[36],"with":[37],"approximately":[38],"7":[39],"billion":[40],"parameters":[41],"this":[43],"dataset":[44,64],"using":[45],"quantized":[46],"low":[47],"rank":[48],"adapters":[49],"(QLoRa).":[50],"Additionally":[51],"we":[52],"also":[53,81],"perform":[54],"zero-shot":[56],"the":[59],"AI2":[60],"reasoning":[61],"challenge":[62],"dev":[63],"order":[66],"check":[68],"if":[69],"OpenStaxQA":[70],"can":[71],"lead":[72],"improved":[75],"performance":[76],"other":[78],"tasks.":[79],"discuss":[82],"broader":[83],"impacts":[84],"relevant":[85],"datasets":[87],"such":[88],"as":[89],"OpenStaxQA.":[90]},"counts_by_year":[],"updated_date":"2026-10-01T08:54:57.152042","created_date":"2025-10-18T00:00:00"}