{"id":"https://openalex.org/W4404306905","doi":"https://doi.org/10.7494/csci.2025.26.4.7689","title":"BIELIK 7B V0.1: POLISH LANGUAGE MODEL - DEVELOPMENT, INSIGHTS, AND EVALUATION","display_name":"BIELIK 7B V0.1: POLISH LANGUAGE MODEL - DEVELOPMENT, INSIGHTS, AND EVALUATION","publication_year":2025,"publication_date":"2025-12-28","ids":{"openalex":"https://openalex.org/W4404306905","doi":"https://doi.org/10.7494/csci.2025.26.4.7689"},"language":"en","primary_location":{"id":"doi:10.7494/csci.2025.26.4.7689","is_oa":true,"landing_page_url":"https://doi.org/10.7494/csci.2025.26.4.7689","pdf_url":"https://journals.agh.edu.pl/csci/article/download/7689/3316","source":{"id":"https://openalex.org/S57947533","display_name":"Computer Science","issn_l":"1508-2806","issn":["1508-2806","2300-7036"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320333","host_organization_name":"Wydawnictwa AGH","host_organization_lineage":["https://openalex.org/P4310320333"],"host_organization_lineage_names":["Wydawnictwa AGH"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://journals.agh.edu.pl/csci/article/download/7689/3316","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114618215","display_name":"Krzysztof Ociepa","orcid":null},"institutions":[{"id":"https://openalex.org/I109266671","display_name":"Autism Speaks","ror":"https://ror.org/04bkad313","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I109266671"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Krzysztof Ociepa","raw_affiliation_strings":["SpeakLeash, Azurro"],"raw_orcid":"https://orcid.org/0009-0006-4858-6460","affiliations":[{"raw_affiliation_string":"SpeakLeash, Azurro","institution_ids":["https://openalex.org/I109266671"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114618216","display_name":"\u0141ukasz Flis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140651","display_name":"Speak Agent (United States)","ror":"https://ror.org/04kbpm904","country_code":"US","type":"company","lineage":["https://openalex.org/I4210140651"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"\u0141ukasz Flis","raw_affiliation_strings":["SpeakLeash, ACK Cyfronet AGH"],"raw_orcid":"https://orcid.org/0009-0001-6509-4250","affiliations":[{"raw_affiliation_string":"SpeakLeash, ACK Cyfronet AGH","institution_ids":["https://openalex.org/I4210140651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091650575","display_name":"Krzysztof Wr\u00f3bel","orcid":"https://orcid.org/0000-0002-3485-7825"},"institutions":[{"id":"https://openalex.org/I126596746","display_name":"Jagiellonian University","ror":"https://ror.org/03bqmcz70","country_code":"PL","type":"education","lineage":["https://openalex.org/I126596746"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Krzysztof Wr\u00f3bel","raw_affiliation_strings":["SpeakLeash, Jagiellonian University, Enelpol"],"raw_orcid":"https://orcid.org/0000-0002-3485-7825","affiliations":[{"raw_affiliation_string":"SpeakLeash, Jagiellonian University, Enelpol","institution_ids":["https://openalex.org/I126596746"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114618217","display_name":"Adrian Gwo\u017adziej","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140651","display_name":"Speak Agent (United States)","ror":"https://ror.org/04kbpm904","country_code":"US","type":"company","lineage":["https://openalex.org/I4210140651"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adrian Gwo\u017adziej","raw_affiliation_strings":["SpeakLeash, ACK Cyfronet AGH"],"raw_orcid":"https://orcid.org/0009-0009-5682-6542","affiliations":[{"raw_affiliation_string":"SpeakLeash, ACK Cyfronet AGH","institution_ids":["https://openalex.org/I4210140651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114618218","display_name":"Remigiusz Kinas","orcid":null},"institutions":[{"id":"https://openalex.org/I109266671","display_name":"Autism Speaks","ror":"https://ror.org/04bkad313","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I109266671"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Remigiusz Kinas","raw_affiliation_strings":["SpeakLeash"],"raw_orcid":"https://orcid.org/0009-0002-0467-7089","affiliations":[{"raw_affiliation_string":"SpeakLeash","institution_ids":["https://openalex.org/I109266671"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5114618215"],"corresponding_institution_ids":["https://openalex.org/I109266671"],"apc_list":null,"apc_paid":null,"fwci":15.1355,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.97985409,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"26","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12658","display_name":"Language and Culture","score":0.9656000137329102,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"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/T12658","display_name":"Language and Culture","score":0.9656000137329102,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4644052982330322},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3673642575740814},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09921684861183167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4644052982330322},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3673642575740814},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09921684861183167}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.7494/csci.2025.26.4.7689","is_oa":true,"landing_page_url":"https://doi.org/10.7494/csci.2025.26.4.7689","pdf_url":"https://journals.agh.edu.pl/csci/article/download/7689/3316","source":{"id":"https://openalex.org/S57947533","display_name":"Computer Science","issn_l":"1508-2806","issn":["1508-2806","2300-7036"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320333","host_organization_name":"Wydawnictwa AGH","host_organization_lineage":["https://openalex.org/P4310320333"],"host_organization_lineage_names":["Wydawnictwa AGH"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2410.18565","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.18565","pdf_url":"https://arxiv.org/pdf/2410.18565","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:ruj.uj.edu.pl:item/460875","is_oa":true,"landing_page_url":"https://ruj.uj.edu.pl/handle/item/460875","pdf_url":"https://arxiv.org/pdf/2410.18565","source":{"id":"https://openalex.org/S4306401249","display_name":"Jagiellonian University Repository (Jagiellonian University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126596746","host_organization_name":"Jagiellonian University","host_organization_lineage":["https://openalex.org/I126596746"],"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":null,"raw_type":"info:eu-repo/semantics/other"},{"id":"pmh:oai:ruj.uj.edu.pl:item/568586","is_oa":true,"landing_page_url":"http://ruj.uj.edu.pl/bitstreams/ba1f2b34-3569-45a7-a645-909654d31d5c/download","pdf_url":"https://journals.agh.edu.pl/csci/article/download/7689/3316/37325","source":{"id":"https://openalex.org/S4306400316","display_name":"Homo Politicus (Academy of Humanities and Economics in Lodz)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":null,"raw_type":"artyku\u0142 w czasopi\u015bmie"},{"id":"doi:10.48550/arxiv.2410.18565","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.18565","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.7494/csci.2025.26.4.7689","is_oa":true,"landing_page_url":"https://doi.org/10.7494/csci.2025.26.4.7689","pdf_url":"https://journals.agh.edu.pl/csci/article/download/7689/3316","source":{"id":"https://openalex.org/S57947533","display_name":"Computer Science","issn_l":"1508-2806","issn":["1508-2806","2300-7036"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320333","host_organization_name":"Wydawnictwa AGH","host_organization_lineage":["https://openalex.org/P4310320333"],"host_organization_lineage_names":["Wydawnictwa AGH"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320326815","display_name":"Infrastruktura PL-Grid","ror":null},{"id":"https://openalex.org/F4320337160","display_name":"Academic Computer Centre Cyfronet, AGH University of Science and Technology","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404306905.pdf","grobid_xml":"https://content.openalex.org/works/W4404306905.grobid-xml"},"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":{"We":[0],"introduce":[1],"Bielik":[2,81],"7B":[3,82],"v0.1,":[4],"a":[5,88,122,130],"7-billion-parameter":[6],"generative":[7],"text":[8],"model":[9,20,26,120],"for":[10,133],"Polish":[11,17,70,109,126],"language":[12,25,127],"processing.":[13],"Trained":[14],"on":[15,56,99],"curated":[16],"corpora,":[18],"this":[19],"addresses":[21],"key":[22],"challenges":[23],"in":[24,93,107,112,125,141],"development":[27],"through":[28],"innovative":[29],"techniques.":[30],"These":[31],"include":[32],"Weighted":[33],"Instruction":[34],"Cross-Entropy":[35],"Loss,":[36],"which":[37,49],"balances":[38],"the":[39,52,64,100,108,142],"learning":[40,53],"of":[41],"different":[42],"instruction":[43],"types,":[44],"and":[45,69,78,115,137],"Adaptive":[46],"Learning":[47],"Rate,":[48],"dynamically":[50],"adjusts":[51],"rate":[54],"based":[55],"training":[57],"progress.":[58],"To":[59],"evaluate":[60],"performance,":[61],"we":[62],"created":[63],"Open":[65],"PL":[66],"LLM":[67],"Leaderboard":[68],"MT-Bench,":[71,110],"novel":[72],"frameworks":[73],"assessing":[74],"various":[75],"NLP":[76],"tasks":[77],"conversational":[79],"abilities.":[80],"v0.1":[83],"demonstrates":[84],"significant":[85],"improvements,":[86],"achieving":[87],"9":[89],"percentage":[90],"point":[91],"increase":[92],"average":[94],"score":[95],"compared":[96],"to":[97],"Mistral-7B-v0.1":[98],"RAG":[101],"Reader":[102],"task.":[103],"It":[104],"also":[105],"excels":[106],"particularly":[111],"Reasoning":[113],"(6.15/10)":[114],"Role-playing":[116],"(7.83/10)":[117],"categories.":[118],"This":[119],"represents":[121],"substantial":[123],"advancement":[124],"AI,":[128],"offering":[129],"powerful":[131],"tool":[132],"diverse":[134],"linguistic":[135],"applications":[136],"setting":[138],"new":[139],"benchmarks":[140],"field.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2024-11-13T00:00:00"}
