{"id":"https://openalex.org/W7117604220","doi":"https://doi.org/10.1109/iccd65941.2025.00089","title":"Llm4mcu-Onto: Leveraging Llms for Automated Ontology Generation From Microcontroller Reference Manual","display_name":"Llm4mcu-Onto: Leveraging Llms for Automated Ontology Generation From Microcontroller Reference Manual","publication_year":2025,"publication_date":"2025-11-10","ids":{"openalex":"https://openalex.org/W7117604220","doi":"https://doi.org/10.1109/iccd65941.2025.00089"},"language":null,"primary_location":{"id":"doi:10.1109/iccd65941.2025.00089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd65941.2025.00089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 43rd International Conference on Computer Design (ICCD)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109812814","display_name":"Asmita Asmita","orcid":"https://orcid.org/0000-0002-5626-1985"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Asmita Asmita","raw_affiliation_strings":["University of California,Electrical and Computer Engineering,Davis,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Electrical and Computer Engineering,Davis,CA,USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013887081","display_name":"Grisha Bandodkar","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grisha Bandodkar","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University,PA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University,PA,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098749111","display_name":"Sujan Ghimire","orcid":"https://orcid.org/0009-0009-1331-0706"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sujan Ghimire","raw_affiliation_strings":["The University of Arizona,Electrical and Computer Engineering,TX,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Arizona,Electrical and Computer Engineering,TX,USA","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113237932","display_name":"Shaurya Srivastav","orcid":null},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaurya Srivastav","raw_affiliation_strings":["University of California,Computer Science,Davis,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Computer Science,Davis,CA,USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016438213","display_name":"Soheil Salehi","orcid":"https://orcid.org/0000-0001-5998-8795"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soheil Salehi","raw_affiliation_strings":["The University of Arizona,Electrical and Computer Engineering,TX,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Arizona,Electrical and Computer Engineering,TX,USA","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121549317","display_name":"Houman Homayoun","orcid":null},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Houman Homayoun","raw_affiliation_strings":["University of California,Electrical and Computer Engineering,Davis,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Electrical and Computer Engineering,Davis,CA,USA","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0292,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82978186,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"582","last_page":"589"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.48170000314712524,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.48170000314712524,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11424","display_name":"Security and Verification in Computing","score":0.08659999817609787,"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/T12122","display_name":"Physical Unclonable Functions (PUFs) and Hardware Security","score":0.042899999767541885,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/firmware","display_name":"Firmware","score":0.7932000160217285},{"id":"https://openalex.org/keywords/microcontroller","display_name":"Microcontroller","score":0.5504000186920166},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5160999894142151},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.512499988079071},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4909999966621399},{"id":"https://openalex.org/keywords/vendor","display_name":"Vendor","score":0.44920000433921814},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.42669999599456787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8138999938964844},{"id":"https://openalex.org/C67212190","wikidata":"https://www.wikidata.org/wiki/Q104851","display_name":"Firmware","level":2,"score":0.7932000160217285},{"id":"https://openalex.org/C173018170","wikidata":"https://www.wikidata.org/wiki/Q165678","display_name":"Microcontroller","level":2,"score":0.5504000186920166},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5160999894142151},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.512499988079071},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4909999966621399},{"id":"https://openalex.org/C2777338717","wikidata":"https://www.wikidata.org/wiki/Q1762621","display_name":"Vendor","level":2,"score":0.44920000433921814},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4307999908924103},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4153999984264374},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3603000044822693},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.328900009393692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3125999867916107},{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28679999709129333},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28049999475479126},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.27720001339912415},{"id":"https://openalex.org/C111065885","wikidata":"https://www.wikidata.org/wiki/Q1189053","display_name":"Fuzz testing","level":3,"score":0.2615000009536743},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25850000977516174},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccd65941.2025.00089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd65941.2025.00089","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 43rd International Conference on Computer Design (ICCD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5562071204185486,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1562482056","https://openalex.org/W2524168323","https://openalex.org/W3164551084","https://openalex.org/W4380551700","https://openalex.org/W4388074146","https://openalex.org/W4391855109","https://openalex.org/W4400647460","https://openalex.org/W4402742291"],"related_works":[],"abstract_inverted_index":{"This":[0,242],"research":[1],"addresses":[2],"the":[3,134,138,161,198,207,244],"challenges":[4,209],"faced":[5],"by":[6],"firmware":[7,253],"developers,":[8],"security":[9,260],"researchers,":[10],"and":[11,46,72,79,151,176,188,219,228,256],"enthusiasts":[12],"who":[13],"work":[14,195],"with":[15,64,113,127,160,225],"low-level":[16],"microcontroller":[17],"(MCU)":[18],"documentation,":[19],"which":[20,103],"often":[21],"spans":[22],"hundreds":[23,236],"of":[24,69,137,193,201,210,237,239],"complex":[25],"pages.":[26],"Current":[27],"structured":[28,74,121,233],"approaches,":[29],"such":[30,249],"as":[31,250],"System":[32],"View":[33],"Description":[34],"(SVD),":[35],"are":[36],"widely":[37],"used":[38],"but":[39],"suffer":[40],"from":[41,81,100,133,178,235],"manual,":[42],"labor-intensive":[43],"creation":[44,218],"processes":[45],"inconsistent":[47],"vendor":[48],"adherence":[49],"to":[50,205,231,246],"CMSIS-SVD":[51,101],"standards.":[52],"We":[53,110,157,214,222],"propose":[54],"an":[55],"automated":[56],"solution":[57],"using":[58,96,145],"Large":[59],"Language":[60],"Models":[61],"(LLMs)":[62],"integrated":[63],"Retrieval-Augmented":[65],"Generation":[66],"(RAG),":[67],"capable":[68],"effectively":[70],"parsing":[71],"extracting":[73,173],"information,":[75],"including":[76],"text,":[77],"tables,":[78],"images":[80],"MCU":[82,179,240],"reference":[83,135,180],"manuals/":[84],"datasheets.":[85],"To":[86],"mitigate":[87],"hallucination":[88],"issues":[89],"inherent":[90],"in":[91,171,197],"LLMs,":[92],"we":[93,104,117],"fine-tuned":[94],"models":[95],"a":[97,119],"dataset":[98],"derived":[99],"files,":[102],"will":[105],"open-source":[106,162],"for":[107,259],"community":[108],"benefit.":[109],"also":[111,158],"experimented":[112,159],"few-shot":[114,229],"models.":[115],"Additionally,":[116],"developed":[118],"standardized":[120,216],"ontology":[122,217],"that":[123],"is":[124],"automatically":[125,172],"populated":[126],"information":[128,177,234],"extracted":[129],"through":[130],"LLM":[131,163],"assistance":[132],"manuals":[136],"corresponding":[139],"MCUs.":[140],"Our":[141],"approach":[142],"was":[143],"evaluated":[144],"OpenAI's":[146],"GPT-4o":[147],"under":[148],"one-shot,":[149],"few-shot,":[150],"fine-tuning":[152],"scenarios,":[153],"all":[154],"incorporating":[155],"RAG.":[156],"model":[164],"CodeLlama.":[165],"The":[166,190],"results":[167],"highlight":[168],"substantial":[169],"improvements":[170],"peripheral":[174],"details":[175],"manuals.":[181],"Thus,":[182],"it":[183],"helps":[184],"reduce":[185],"manual":[186],"effort":[187],"time.":[189],"key":[191],"contribution":[192],"our":[194],"lies":[196],"tailored":[199],"adaptation":[200],"existing":[202],"AI":[203],"techniques":[204],"address":[206],"specific":[208],"embedded":[211],"systems":[212],"documentation.":[213,241],"perform":[215],"multimodal":[220],"parsing.":[221],"leverage":[223],"RAG":[224],"MCU-specific":[226],"finetuning":[227],"learning":[230],"generate":[232],"pages":[238],"opens":[243],"door":[245],"potential":[247],"applications":[248],"more":[251],"accurate":[252],"code":[254],"generation":[255],"reverse":[257],"engineering":[258],"analysis.":[261]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-12-30T00:00:00"}
