{"id":"https://openalex.org/W7161132378","doi":"https://doi.org/10.48550/arxiv.2605.12516","title":"Domain Adaptation of Large Language Models for Polymer-Composite Additive Manufacturing Using Retrieval-Augmented Generation and Fine-Tuning","display_name":"Domain Adaptation of Large Language Models for Polymer-Composite Additive Manufacturing Using Retrieval-Augmented Generation and Fine-Tuning","publication_year":2026,"publication_date":"2026-04-02","ids":{"openalex":"https://openalex.org/W7161132378","doi":"https://doi.org/10.48550/arxiv.2605.12516"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.12516","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.12516","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,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.12516","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136161369","display_name":"Saiful Islam Sagor","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sagor, Saiful Islam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113191858","display_name":"Tania Haghighi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haghighi, Tania","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072253597","display_name":"Minhaj Nur Alam","orcid":"https://orcid.org/0000-0003-3095-2232"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alam, Minhaj Nur","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084215390","display_name":"Erina Baynojir Joyee","orcid":"https://orcid.org/0000-0002-1506-6809"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joyee, Erina Baynojir","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.31690001487731934,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.31690001487731934,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2467000037431717,"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":0.07020000368356705,"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/domain","display_name":"Domain (mathematical analysis)","score":0.654699981212616},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6539999842643738},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6312000155448914},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6111000180244446},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.5720999836921692},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5658000111579895},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.541100025177002},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.39750000834465027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6822999715805054},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.654699981212616},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6539999842643738},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6312000155448914},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6111000180244446},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.5720999836921692},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5658000111579895},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.541100025177002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5267999768257141},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4819999933242798},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4041000008583069},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.39750000834465027},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C92548554","wikidata":"https://www.wikidata.org/wiki/Q2262868","display_name":"Domain model","level":3,"score":0.3547999858856201},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3296000063419342},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3197000026702881},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27390000224113464},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C135257023","wikidata":"https://www.wikidata.org/wiki/Q691358","display_name":"Domain-specific language","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.2547999918460846},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.12516","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.12516","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,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.12516","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.12516","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,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6546719670295715,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"General-purpose":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"often":[5],"struggle":[6],"to":[7,16,23,37,45,84,94,239],"generate":[8],"reliable":[9],"responses":[10,181],"in":[11,43,212,221],"specialized":[12,240],"engineering":[13,156,241],"domains":[14,242],"due":[15],"limited":[17],"domain":[18,42,143],"grounding":[19],"and":[20,50,71,86,101,111,136,161,190,217],"insufficient":[21],"exposure":[22],"structured":[24],"technical":[25,69,248],"knowledge.":[26],"This":[27],"study":[28],"investigates":[29],"practical":[30],"strategies":[31],"for":[32,52,158,236],"adapting":[33,237],"a":[34,107,124,133,138,232],"foundation":[35],"LLM":[36],"the":[38,119,167,172,175],"additive":[39],"manufacturing":[40],"(AM)":[41],"order":[44],"improve":[46],"answer":[47],"accuracy,":[48,159],"relevance,":[49,160],"usability":[51],"expert-level":[53],"question":[54],"answering.":[55],"AM":[56,109,151,204],"knowledge":[57],"is":[58,146],"distributed":[59],"across":[60],"heterogeneous":[61],"sources":[62],"such":[63,88],"as":[64],"academic":[65],"literature,":[66],"manufacturer":[67],"documentation,":[68],"standards,":[70],"procedural":[72],"guides.":[73],"Although":[74],"general":[75],"LLMs":[76,238],"demonstrate":[77],"strong":[78],"linguistic":[79],"capabilities,":[80],"they":[81],"frequently":[82],"fail":[83],"retrieve":[85],"contextualize":[87],"domain-specific":[89,99],"information.":[90],"Two":[91],"common":[92],"approaches":[93,230],"address":[95],"this":[96],"limitation":[97],"are":[98,182,187,192],"fine-tuning":[100,201,245],"retrieval-augmented":[102,229],"generation":[103],"(RAG).":[104],"We":[105],"construct":[106],"curated":[108],"corpus":[110],"evaluate":[112],"three":[113],"configurations":[114],"based":[115],"on":[116,141,202,246],"LLaMA-3-8B:":[117],"(1)":[118],"pretrained":[120],"baseline":[121,197],"model,":[122],"(2)":[123],"RAG":[125,168,180],"system":[126],"that":[127,166,228],"retrieves":[128],"relevant":[129,195,219],"document":[130],"chunks":[131],"from":[132],"vector":[134],"database,":[135],"(3)":[137],"model":[139,169],"fine-tuned":[140],"raw":[142,203],"text.":[144],"Performance":[145],"evaluated":[147],"using":[148],"200":[149,176],"expert-designed":[150],"questions":[152],"assessed":[153],"by":[154],"mechanical":[155],"experts":[157],"overall":[162],"preference.":[163],"Results":[164],"show":[165],"consistently":[170],"outperforms":[171],"baseline.":[173],"Among":[174],"questions,":[177],"75.5%":[178],"of":[179,215,223],"judged":[183],"more":[184,194,209,218,233],"accurate,":[185],"85.2%":[186],"preferred":[188],"overall,":[189],"90.8%":[191],"rated":[193],"than":[196,243],"responses.":[198],"In":[199],"contrast,":[200],"text":[205],"reduces":[206],"performance,":[207],"producing":[208],"accurate":[210],"answers":[211,220],"only":[213],"5.6%":[214],"cases":[216],"32.5%":[222],"cases.":[224],"These":[225],"results":[226],"indicate":[227],"provide":[231],"effective":[234],"pathway":[235],"naive":[244],"unstructured":[247],"data.":[249]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-15T00:00:00"}