{"id":"https://openalex.org/W4415799219","doi":"https://doi.org/10.52202/079017-0046","title":"SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models","display_name":"SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4415799219","doi":"https://doi.org/10.52202/079017-0046"},"language":"en","primary_location":{"id":"doi:10.52202/079017-0046","doi":"https://doi.org/10.52202/079017-0046","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-0046","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2401.07950","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100456041","display_name":"Dan Zhang","orcid":"https://orcid.org/0000-0002-7295-4837","observed_orcids":["https://orcid.org/0000-0002-7295-4837"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018336656","display_name":"Zhengxiao Du","orcid":"https://orcid.org/0000-0002-8223-4147","observed_orcids":["https://orcid.org/0000-0002-8223-4147"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziniu Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093734261","display_name":"Sining Zhoubian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sining Zhoubian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018336656","display_name":"Zhengxiao Du","orcid":"https://orcid.org/0000-0002-8223-4147","observed_orcids":["https://orcid.org/0000-0002-8223-4147"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengxiao Du","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100524243","display_name":"Kaiyu Yang","orcid":"https://orcid.org/0009-0009-9602-005X","observed_orcids":["https://orcid.org/0009-0009-9602-005X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaiyu Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101789196","display_name":"Zihan Wang","orcid":"https://orcid.org/0000-0002-0093-4263","observed_orcids":["https://orcid.org/0000-0002-0093-4263"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zihan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085826758","display_name":"Yisong Yue","orcid":"https://orcid.org/0000-0001-9127-1989","observed_orcids":["https://orcid.org/0000-0001-9127-1989"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yisong Yue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052284218","display_name":"Yuxiao Dong","orcid":"https://orcid.org/0000-0002-6092-2002","observed_orcids":["https://orcid.org/0000-0002-6092-2002"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxiao Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100670350","display_name":"Jie Tang","orcid":"https://orcid.org/0000-0001-8602-7754","observed_orcids":["https://orcid.org/0000-0001-8602-7754"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Tang","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":2.3098,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91009432,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1443","last_page":"1473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6122999787330627,"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":0.6122999787330627,"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":0.17430000007152557,"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":0.07199999690055847,"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/annotated-data","display_name":"annotated dataset","score":0.8299999833106995},{"id":"https://openalex.org/keywords/instruction-tuning","display_name":"instruction tuning","score":0.6150000095367432},{"id":"https://openalex.org/keywords/self-reflection","display_name":"self-reflection","score":0.453000009059906},{"id":"https://openalex.org/keywords/scientific-writing","display_name":"scientific writing","score":0.40799999237060547},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.42500001192092896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.65829998254776},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6147000193595886},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4771000146865845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4429999887943268},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.30640000104904175},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.2547000050544739},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/079017-0046","doi":"https://doi.org/10.52202/079017-0046","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-0046","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2401.07950","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.07950","pdf_url":"https://arxiv.org/pdf/2401.07950","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.2401.07950","doi":"https://doi.org/10.48550/arxiv.2401.07950","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2401.07950","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:2401.07950","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.07950","pdf_url":"https://arxiv.org/pdf/2401.07950","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":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.5385000109672546}],"study_designs":[],"awards":[{"id":"https://openalex.org/G6048029205","display_name":null,"funder_award_id":"62276148","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6694531218","display_name":null,"funder_award_id":"62425601","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415799219.pdf","grobid_xml":"https://content.openalex.org/works/W4415799219.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4399657214","https://openalex.org/W7123371188","https://openalex.org/W4415987149","https://openalex.org/W7120024926","https://openalex.org/W7204484264","https://openalex.org/W7108340679","https://openalex.org/W4392011693","https://openalex.org/W4404780528","https://openalex.org/W4403809298","https://openalex.org/W7128518386"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"shown":[5],"promise":[6],"in":[7,20,72],"assisting":[8],"scientific":[9,23,43,47,53,87,155],"discovery.":[10],"However,":[11],"such":[12],"applications":[13],"are":[14],"currently":[15],"limited":[16],"by":[17,90],"LLMs'":[18],"deficiencies":[19],"understanding":[21,164],"intricate":[22],"concepts,":[24],"deriving":[25],"symbolic":[26],"equations,":[27],"and":[28,103,110,147,150,156,174],"solving":[29],"advanced":[30],"numerical":[31],"calculations.":[32],"To":[33,131],"bridge":[34],"these":[35],"gaps,":[36],"we":[37,99,137],"introduce":[38],"SciInstruct,":[39,136,143],"a":[40,60,91,101],"suite":[41],"of":[42,51,93,135,166],"instructions":[44],"for":[45,85],"training":[46],"language":[48,140,163],"models":[49,141],"capable":[50],"college-level":[52],"reasoning.":[54],"Central":[55],"to":[56,66,81],"our":[57],"approach":[58],"is":[59],"novel":[61],"self-reflective":[62,94],"instruction":[63],"annotation":[64],"framework":[65,77],"address":[67],"the":[68,73,115,133,162,167],"data":[69],"scarcity":[70],"challenge":[71],"science":[74],"domain.":[75],"This":[76],"leverages":[78],"existing":[79],"LLMs":[80],"generate":[82],"step-by-step":[83],"reasoning":[84,158],"unlabelled":[86],"questions,":[88],"followed":[89],"process":[92],"critic-and-revise.":[95],"Applying":[96],"this":[97],"framework,":[98],"curated":[100,116],"diverse":[102],"high-quality":[104],"dataset":[105],"encompassing":[106],"physics,":[107],"chemistry,":[108],"math,":[109],"formal":[111],"proofs.":[112],"We":[113,170],"analyze":[114],"SciInstruct":[117,175],"from":[118],"multiple":[119],"interesting":[120],"perspectives":[121],"(e.g.,":[122],"domain,":[123],"scale,":[124],"source,":[125],"question":[126],"type,":[127],"answer":[128],"length,":[129],"etc.).":[130],"verify":[132],"effectiveness":[134],"fine-tuned":[138],"different":[139],"with":[142],"i.e.,":[144],"ChatGLM3":[145],"(6B":[146],"32B),":[148],"Llama3-8B-Instruct,":[149],"Mistral-7B:":[151],"MetaMath,":[152],"enhancing":[153],"their":[154],"mathematical":[157],"capabilities,":[159],"without":[160],"sacrificing":[161],"capabilities":[165],"base":[168],"model.":[169],"release":[171],"all":[172],"codes":[173],"at":[176],"https://github.com/THUDM/SciGLM.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-15T10:00:46.086208","created_date":"2025-11-03T00:00:00"}