{"id":"https://openalex.org/W7134068130","doi":"https://doi.org/10.1093/bib/bbag089","title":"Benchmarking large language models for pathogen\u2013disease classification in post-acute infection syndromes","display_name":"Benchmarking large language models for pathogen\u2013disease classification in post-acute infection syndromes","publication_year":2026,"publication_date":"2026-02-13","ids":{"openalex":"https://openalex.org/W7134068130","doi":"https://doi.org/10.1093/bib/bbag089","pmid":"https://pubmed.ncbi.nlm.nih.gov/41789566"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbag089","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbag089","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1093/bib/bbag089","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120083400","display_name":"Syed Mohammed Khalid","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Syed Mohammed Khalid","raw_affiliation_strings":["Clinical Bioinformatics, Saarland University , 66123 Saarbr\u00fccken ,"],"raw_orcid":"https://orcid.org/0009-0007-6482-119X","affiliations":[{"raw_affiliation_string":"Clinical Bioinformatics, Saarland University , 66123 Saarbr\u00fccken ,","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128277891","display_name":"Tom W\u00f6lker","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tom W\u00f6lker","raw_affiliation_strings":["Clinical Bioinformatics, Saarland University , 66123 Saarbr\u00fccken ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clinical Bioinformatics, Saarland University , 66123 Saarbr\u00fccken ,","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047318557","display_name":"Leidy-Alejandra G Molano","orcid":"https://orcid.org/0000-0003-0069-6098"},"institutions":[{"id":"https://openalex.org/I4210142777","display_name":"Helmholtz Institute for Pharmaceutical Research Saarland","ror":"https://ror.org/042dsac10","country_code":"DE","type":"government","lineage":["https://openalex.org/I1305996414","https://openalex.org/I4210124929","https://openalex.org/I4210142777"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Leidy-Alejandra G Molano","raw_affiliation_strings":["Clinical Bioinformatics, Saarland University , 66123 Saarbr\u00fccken ,","Helmholtz Institute for Pharmaceutical Research Saarland (HIPS)\u2013Helmholtz Centre for Infection Research (HZI), Saarland University Campus , 66123 Saarbr\u00fccken ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clinical Bioinformatics, Saarland University , 66123 Saarbr\u00fccken ,","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Helmholtz Institute for Pharmaceutical Research Saarland (HIPS)\u2013Helmholtz Centre for Infection Research (HZI), Saarland University Campus , 66123 Saarbr\u00fccken ,","institution_ids":["https://openalex.org/I4210142777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093323088","display_name":"Simon Graf","orcid":"https://orcid.org/0009-0002-9913-4916"},"institutions":[{"id":"https://openalex.org/I4210142777","display_name":"Helmholtz Institute for Pharmaceutical Research Saarland","ror":"https://ror.org/042dsac10","country_code":"DE","type":"government","lineage":["https://openalex.org/I1305996414","https://openalex.org/I4210124929","https://openalex.org/I4210142777"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Simon Graf","raw_affiliation_strings":["Clinical Bioinformatics, Saarland University , 66123 Saarbr\u00fccken ,","Helmholtz Institute for Pharmaceutical Research Saarland (HIPS)\u2013Helmholtz Centre for Infection Research (HZI), Saarland University Campus , 66123 Saarbr\u00fccken ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clinical Bioinformatics, Saarland University , 66123 Saarbr\u00fccken ,","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Helmholtz Institute for Pharmaceutical Research Saarland (HIPS)\u2013Helmholtz Centre for Infection Research (HZI), Saarland University Campus , 66123 Saarbr\u00fccken ,","institution_ids":["https://openalex.org/I4210142777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013571225","display_name":"Andreas Keller","orcid":"https://orcid.org/0000-0001-5491-2214"},"institutions":[{"id":"https://openalex.org/I4210142777","display_name":"Helmholtz Institute for Pharmaceutical Research Saarland","ror":"https://ror.org/042dsac10","country_code":"DE","type":"government","lineage":["https://openalex.org/I1305996414","https://openalex.org/I4210124929","https://openalex.org/I4210142777"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Keller","raw_affiliation_strings":["Clinical Bioinformatics, Saarland University , 66123 Saarbr\u00fccken ,","Helmholtz Institute for Pharmaceutical Research Saarland (HIPS)\u2013Helmholtz Centre for Infection Research (HZI), Saarland University Campus , 66123 Saarbr\u00fccken ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clinical Bioinformatics, Saarland University , 66123 Saarbr\u00fccken ,","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Helmholtz Institute for Pharmaceutical Research Saarland (HIPS)\u2013Helmholtz Centre for Infection Research (HZI), Saarland University Campus , 66123 Saarbr\u00fccken ,","institution_ids":["https://openalex.org/I4210142777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5120083400"],"corresponding_institution_ids":["https://openalex.org/I91712215"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":{"value":4011,"currency":"USD","value_usd":4011},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42443843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"2","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":0.18469999730587006,"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":0.18469999730587006,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.1006999984383583,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.07370000332593918,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7071999907493591},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6460000276565552},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6114000082015991},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6100999712944031},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.42890000343322754},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42730000615119934},{"id":"https://openalex.org/keywords/multiple-models","display_name":"Multiple Models","score":0.3946000039577484}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7071999907493591},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.676800012588501},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6460000276565552},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6114000082015991},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6100999712944031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5892000198364258},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5533000230789185},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5372999906539917},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.42890000343322754},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.3946000039577484},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.374099999666214},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2703000009059906},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2685000002384186},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.263700008392334}],"mesh":[{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":"Q000821","qualifier_name":"virology","is_major_topic":true},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":"Q000821","qualifier_name":"virology","is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000472","qualifier_name":"pathogenicity","is_major_topic":false},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000472","qualifier_name":"pathogenicity","is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007251","descriptor_name":"Influenza, Human","qualifier_ui":"Q000821","qualifier_name":"virology","is_major_topic":false},{"descriptor_ui":"D007251","descriptor_name":"Influenza, Human","qualifier_ui":"Q000821","qualifier_name":"virology","is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bib/bbag089","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbag089","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41789566","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41789566","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12963971","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12963971/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12963971/pdf/bbag089.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Brief Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bib/bbag089","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bib/bbag089","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8481464809","display_name":null,"funder_award_id":"469073465","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320308022","display_name":"California Department of Fish and Game","ror":"https://ror.org/02v6w2r95"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1911030455","https://openalex.org/W2142678031","https://openalex.org/W2807176368","https://openalex.org/W2904322551","https://openalex.org/W2911489562","https://openalex.org/W2970482702","https://openalex.org/W2974429973","https://openalex.org/W3119322361","https://openalex.org/W4205972999","https://openalex.org/W4226278401","https://openalex.org/W4280516114","https://openalex.org/W4292779060","https://openalex.org/W4316014106","https://openalex.org/W4367623495","https://openalex.org/W4380154528","https://openalex.org/W4381309298","https://openalex.org/W4385245566","https://openalex.org/W4385260875","https://openalex.org/W4385416665","https://openalex.org/W4385819901","https://openalex.org/W4386718985","https://openalex.org/W4387729185","https://openalex.org/W4388615775","https://openalex.org/W4389116614","https://openalex.org/W4389156617","https://openalex.org/W4389519607","https://openalex.org/W4389523765","https://openalex.org/W4391126287","https://openalex.org/W4391494845","https://openalex.org/W4391833078","https://openalex.org/W4391940656","https://openalex.org/W4391973028","https://openalex.org/W4395474395","https://openalex.org/W4396673725","https://openalex.org/W4397047623","https://openalex.org/W4401306886","https://openalex.org/W4401759841","https://openalex.org/W4403123652","https://openalex.org/W4403883673","https://openalex.org/W4404330874","https://openalex.org/W4405183733","https://openalex.org/W4405354744","https://openalex.org/W4405655184","https://openalex.org/W4406766910","https://openalex.org/W4409474031","https://openalex.org/W4411119577","https://openalex.org/W4414281281"],"related_works":[],"abstract_inverted_index":{"Post-Acute":[0],"Infection":[1],"Syndromes":[2],"(PAIS)":[3],"are":[4],"medical":[5],"conditions":[6],"that":[7,139],"persist":[8],"following":[9],"acute":[10],"infections":[11],"from":[12],"pathogens":[13],"such":[14,53,122,194],"as":[15,123,195],"SARS-CoV-2,":[16],"Epstein-Barr":[17],"virus,":[18],"and":[19,28,57,110,126,146,157,165,183,197,202],"Influenza":[20],"virus.":[21],"Despite":[22],"growing":[23],"global":[24],"awareness":[25],"of":[26,39,49,70,88,99,102,128,163,172],"PAIS":[27],"the":[29,47,68,116,152],"exponential":[30],"increase":[31],"in":[32,75,189],"biomedical":[33],"literature,":[34],"only":[35],"a":[36,54,60,80,85,96],"small":[37],"fraction":[38],"this":[40],"literature":[41],"pertains":[42],"specifically":[43],"to":[44,118,174],"PAIS,":[45],"making":[46],"identification":[48],"pathogen-disease":[50],"associations":[51,78],"within":[52],"vast,":[55],"heterogeneous,":[56],"unstructured":[58],"corpus":[59],"significant":[61],"challenge":[62],"for":[63],"researchers.":[64],"This":[65],"study":[66],"evaluated":[67],"effectiveness":[69],"large":[71],"language":[72],"models":[73,193],"(LLMs)":[74],"extracting":[76],"these":[77],"through":[79],"binary":[81],"classification":[82,134],"task":[83],"using":[84],"curated":[86],"dataset":[87],"1000":[89],"manually":[90],"labeled":[91],"PubMed":[92],"abstracts.":[93],"We":[94,113],"benchmarked":[95],"wide":[97],"range":[98],"open-source":[100],"LLMs":[101],"varying":[103],"sizes":[104],"(4B-70B":[105],"parameters),":[106],"including":[107],"generalist,":[108],"reasoning,":[109],"biomedical-specific":[111],"models.":[112],"also":[114],"investigated":[115],"extent":[117],"which":[119],"prompting":[120,147,150,185],"strategies":[121],"zero-shot,":[124],"few-shot,":[125],"Chain":[127],"Thought":[129],"(CoT)":[130],"methods":[131],"can":[132],"improve":[133],"performance.":[135],"Our":[136],"results":[137],"indicate":[138],"model":[140],"performance":[141,188],"varied":[142],"by":[143],"size,":[144],"architecture,":[145],"strategy.":[148],"Zero-shot":[149],"produced":[151],"most":[153],"reliable":[154],"results:":[155],"Mistral-Small-Instruct-2409":[156],"Llama-3.1-Nemotron-70B-Instruct":[158],"achieved":[159],"balanced":[160],"accuracy":[161,201],"scores":[162,171],"0.81":[164],"0.80,":[166,175],"respectively,":[167],"along":[168],"with":[169,206],"macro-F1":[170],"up":[173],"while":[176],"maintaining":[177],"minimal":[178],"invalid":[179],"outputs.":[180],"While":[181],"few-shot":[182],"CoT":[184],"often":[186],"degraded":[187],"generalist":[190],"models,":[191],"reasoning":[192],"DeepSeek-R1-Distill-Llama-70B":[196],"QwQ-32B":[198],"demonstrated":[199],"improved":[200],"consistency":[203],"when":[204],"provided":[205],"additional":[207],"context.":[208]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-03-07T00:00:00"}
