{"id":"https://openalex.org/W7135097061","doi":"https://doi.org/10.1016/j.caeai.2026.100577","title":"FermBench: A new benchmark for measuring the capabilities of LLMs on fermentation knowledge","display_name":"FermBench: A new benchmark for measuring the capabilities of LLMs on fermentation knowledge","publication_year":2026,"publication_date":"2026-03-12","ids":{"openalex":"https://openalex.org/W7135097061","doi":"https://doi.org/10.1016/j.caeai.2026.100577"},"language":"en","primary_location":{"id":"doi:10.1016/j.caeai.2026.100577","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.caeai.2026.100577","pdf_url":null,"source":{"id":"https://openalex.org/S4210183364","display_name":"Computers and Education Artificial Intelligence","issn_l":"2666-920X","issn":["2666-920X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers and Education: Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.caeai.2026.100577","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071319377","display_name":"Fiammetta Caccavale","orcid":"https://orcid.org/0000-0003-0795-5988"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Fiammetta Caccavale","raw_affiliation_strings":["Process and System Engineering Centre (PROSYS), Department of Chemical and Biochemical Engineering, Technical University of Denmark, S\u00f8ltofts Plads, Building 228A, 2800 Kgs. Lyngby, Denmark"],"raw_orcid":"https://orcid.org/0000-0003-0795-5988","affiliations":[{"raw_affiliation_string":"Process and System Engineering Centre (PROSYS), Department of Chemical and Biochemical Engineering, Technical University of Denmark, S\u00f8ltofts Plads, Building 228A, 2800 Kgs. Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076146831","display_name":"Adem R.N. Aouichaoui","orcid":"https://orcid.org/0000-0002-3297-6054"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Adem R.N. Aouichaoui","raw_affiliation_strings":["Department of Energy Conversion and Storage, Technical University of Denmark, Agnes Nielsens Vej, Building 301, 2800 Kgs. Lyngby, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-3297-6054","affiliations":[{"raw_affiliation_string":"Department of Energy Conversion and Storage, Technical University of Denmark, Agnes Nielsens Vej, Building 301, 2800 Kgs. Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057276095","display_name":"Ulrich Kr\u00fchne","orcid":"https://orcid.org/0000-0001-7774-7442"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Ulrich Kr\u00fchne","raw_affiliation_strings":["Process and System Engineering Centre (PROSYS), Department of Chemical and Biochemical Engineering, Technical University of Denmark, S\u00f8ltofts Plads, Building 228A, 2800 Kgs. Lyngby, Denmark"],"raw_orcid":"https://orcid.org/0000-0001-7774-7442","affiliations":[{"raw_affiliation_string":"Process and System Engineering Centre (PROSYS), Department of Chemical and Biochemical Engineering, Technical University of Denmark, S\u00f8ltofts Plads, Building 228A, 2800 Kgs. Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021629663","display_name":"Krist V. Gernaey","orcid":"https://orcid.org/0000-0002-0364-1773"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Krist V. Gernaey","raw_affiliation_strings":["Process and System Engineering Centre (PROSYS), Department of Chemical and Biochemical Engineering, Technical University of Denmark, S\u00f8ltofts Plads, Building 228A, 2800 Kgs. Lyngby, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-0364-1773","affiliations":[{"raw_affiliation_string":"Process and System Engineering Centre (PROSYS), Department of Chemical and Biochemical Engineering, Technical University of Denmark, S\u00f8ltofts Plads, Building 228A, 2800 Kgs. Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065707905","display_name":"Carina L. Gargalo","orcid":"https://orcid.org/0000-0002-8740-9591"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Carina L. Gargalo","raw_affiliation_strings":["Process and System Engineering Centre (PROSYS), Department of Chemical and Biochemical Engineering, Technical University of Denmark, S\u00f8ltofts Plads, Building 228A, 2800 Kgs. Lyngby, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-8740-9591","affiliations":[{"raw_affiliation_string":"Process and System Engineering Centre (PROSYS), Department of Chemical and Biochemical Engineering, Technical University of Denmark, S\u00f8ltofts Plads, Building 228A, 2800 Kgs. Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5071319377"],"corresponding_institution_ids":["https://openalex.org/I96673099"],"apc_list":{"value":1800,"currency":"USD","value_usd":1800},"apc_paid":{"value":1800,"currency":"USD","value_usd":1800},"fwci":8.0655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96363317,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"10","issue":null,"first_page":"100577","last_page":"100577"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10284","display_name":"Anaerobic Digestion and Biogas Production","score":0.08980000019073486,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10284","display_name":"Anaerobic Digestion and Biogas Production","score":0.08980000019073486,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.06319999694824219,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"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"}},{"id":"https://openalex.org/T10932","display_name":"Microbial Metabolic Engineering and Bioproduction","score":0.050700001418590546,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"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/benchmark","display_name":"Benchmark (surveying)","score":0.4948999881744385},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43630000948905945},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3594000041484833},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.31869998574256897}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4948999881744385},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4553000032901764},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43630000948905945},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.37770000100135803},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3594000041484833},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3594000041484833},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C100544194","wikidata":"https://www.wikidata.org/wiki/Q41760","display_name":"Fermentation","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C134560507","wikidata":"https://www.wikidata.org/wiki/Q753291","display_name":"Environmental economics","level":1,"score":0.2888000011444092},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.28769999742507935},{"id":"https://openalex.org/C175605778","wikidata":"https://www.wikidata.org/wiki/Q3299701","display_name":"Natural resource economics","level":1,"score":0.2628999948501587}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.caeai.2026.100577","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.caeai.2026.100577","pdf_url":null,"source":{"id":"https://openalex.org/S4210183364","display_name":"Computers and Education Artificial Intelligence","issn_l":"2666-920X","issn":["2666-920X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers and Education: Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.caeai.2026.100577","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.caeai.2026.100577","pdf_url":null,"source":{"id":"https://openalex.org/S4210183364","display_name":"Computers and Education Artificial Intelligence","issn_l":"2666-920X","issn":["2666-920X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers and Education: Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2","score":0.6314775943756104}],"awards":[{"id":"https://openalex.org/G1520909536","display_name":null,"funder_award_id":"Sustain4.0","funder_id":"https://openalex.org/F4320325957","funder_display_name":"Novo Nordisk Fonden"},{"id":"https://openalex.org/G462722547","display_name":null,"funder_award_id":"PNNF22OC0080136","funder_id":"https://openalex.org/F4320325957","funder_display_name":"Novo Nordisk Fonden"},{"id":"https://openalex.org/G7808997556","display_name":null,"funder_award_id":"101159993","funder_id":"https://openalex.org/F4320334322","funder_display_name":"HORIZON EUROPE Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320323153","display_name":"Danmarks Tekniske Universitet","ror":"https://ror.org/04qtj9h94"},{"id":"https://openalex.org/F4320325957","display_name":"Novo Nordisk Fonden","ror":"https://ror.org/04txyc737"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2016944307","https://openalex.org/W2294798173","https://openalex.org/W4226019252","https://openalex.org/W4241727697","https://openalex.org/W4282839633","https://openalex.org/W4323655724","https://openalex.org/W4375858605","https://openalex.org/W4379799312","https://openalex.org/W4385632485","https://openalex.org/W4385878593","https://openalex.org/W4399665471","https://openalex.org/W4400032145","https://openalex.org/W4400942437","https://openalex.org/W4401208776","https://openalex.org/W4406496476","https://openalex.org/W4407657137"],"related_works":[],"abstract_inverted_index":{"Generative":[0],"Artificial":[1],"Intelligence":[2],"(GenAI)":[3],"chatbots":[4,57],"continue":[5],"to":[6,42,70,87,91,117,177],"amaze":[7],"users":[8],"worldwide":[9],"with":[10,80],"their":[11],"rapid":[12],"improvements.":[13],"These":[14,209],"tools":[15],"possess":[16],"vast":[17],"general":[18],"knowledge":[19,186],"and":[20,50,89,134,156,169,193],"can":[21],"thus":[22],"be":[23,205,220],"used":[24,206],"in":[25,36,75,207,238],"various":[26],"fields,":[27],"including":[28,129],"education.":[29,208],"However,":[30],"before":[31],"rolling":[32],"out":[33],"these":[34,73,142,189],"models":[35,122,190],"pedagogical":[37,199],"applications,":[38],"it":[39],"is":[40,48,69,191,247],"fundamental":[41],"understand":[43],"whether":[44],"the":[45,54,81,93,114,139,157,166,170,173,184,194,213,235,245],"information":[46],"provided":[47],"reliable":[49],"if":[51],"any":[52],"of":[53,66,84,141,215,244],"currently":[55],"available":[56,126],"are":[58,251],"best":[59,94,182],"suited":[60],"for":[61,109],"domain-specific":[62],"tasks.":[63],"The":[64,160],"objective":[65],"this":[67,99],"study":[68,246],"thoroughly":[71],"investigate":[72],"aspects":[74],"a":[76,105,146],"specific":[77],"domain,":[78],"fermentation,":[79],"overarching":[82],"goal":[83],"providing":[85],"guidelines":[86,200],"students":[88],"teachers":[90],"select":[92],"GenAI":[95,127,217],"assistant.":[96],"To":[97,137],"achieve":[98],"goal,":[100],"we":[101,144],"introduce":[102],"FermBench":[103],",":[104],"dataset":[106],"specifically":[107],"designed":[108],"fermentation":[110],"processes.":[111],"We":[112],"use":[113],"collected":[115],"data":[116],"benchmark":[118],"five":[119],"large":[120],"language":[121],"(LLMs)":[123],"powering":[124],"commercially":[125],"chatbots,":[128],"ChatGPT,":[130],"Gemini,":[131],"DeepSeek,":[132],"Claude":[133],"le":[135],"Chat.":[136],"evaluate":[138],"responses":[140],"models,":[143],"propose":[145],"robust":[147],"experimental":[148],"framework":[149],"that":[150,172,212,248],"includes":[151],"automated":[152],"metrics,":[153],"human":[154],"annotations,":[155],"LLM-as-a-Judge":[158],"approach.":[159],"obtained":[161],"results":[162,196,210],"suggest":[163,211],"that,":[164],"given":[165],"high":[167],"baseline":[168],"fact":[171],"judges":[174],"were":[175],"unable":[176],"agree":[178],"on":[179],"an":[180],"overall":[181],"model,":[183],"current":[185],"embedded":[187],"within":[188],"adequate":[192],"standalone":[195],"cannot":[197],"provide":[198],"regarding":[201],"which":[202,216],"chatbot":[203,218],"should":[204,219],"choice":[214],"supported":[221],"by":[222,234],"institutional":[223],"or":[224],"government":[225],"guidance,":[226],"as":[227,229],"well":[228],"individual":[230],"preferences,":[231],"perhaps":[232],"informed":[233],"parameters":[236],"identified":[237],"our":[239],"analysis.":[240],"An":[241],"interesting":[242],"finding":[243],"curated":[249],"answers":[250],"not":[252],"necessarily":[253],"better":[254],"than":[255],"generated":[256],"ones.":[257]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2026-03-13T00:00:00"}
