{"id":"https://openalex.org/W7204180116","doi":"https://doi.org/10.48550/arxiv.2608.22817","title":"Industrial-Instruction: An End-to-End Framework for Building Instruction-Tuning and Benchmark Datasets from Industrial Technical Reports","display_name":"Industrial-Instruction: An End-to-End Framework for Building Instruction-Tuning and Benchmark Datasets from Industrial Technical Reports","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204180116","doi":"https://doi.org/10.48550/arxiv.2608.22817"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.22817","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22817","pdf_url":"https://arxiv.org/pdf/2608.22817","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"},"parent_works":[],"lineage":["https://openalex.org/W7204180116"],"child_works_count":0,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.22817","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116392550","display_name":"Parsa Bakhtiari","orcid":"https://orcid.org/0009-0006-5512-0722","observed_orcids":["https://orcid.org/0009-0006-5512-0722"]},"institutions":[{"id":"https://openalex.org/I4210107186","display_name":"Hamedan University of Technology","ror":"https://ror.org/01hgb6e08","country_code":"IR","type":"education","lineage":["https://openalex.org/I4210107186"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Bakhtiari, Parsa","raw_affiliation_strings":["Department of Computer Engineering , Hamedan University of Technology , Hamedan , Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering , Hamedan University of Technology , Hamedan , Iran","institution_ids":["https://openalex.org/I4210107186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113663041","display_name":"Hassan Bashiri","orcid":"https://orcid.org/0000-0001-5429-5375","observed_orcids":["https://orcid.org/0000-0001-5429-5375"]},"institutions":[{"id":"https://openalex.org/I4210107186","display_name":"Hamedan University of Technology","ror":"https://ror.org/01hgb6e08","country_code":"IR","type":"education","lineage":["https://openalex.org/I4210107186"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Bashiri, Hassan","raw_affiliation_strings":["Department of Computer Engineering , Hamedan University of Technology , Hamedan , Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering , Hamedan University of Technology , Hamedan , Iran","institution_ids":["https://openalex.org/I4210107186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005916463","display_name":"Alireza Khalilipour","orcid":"https://orcid.org/0000-0002-0397-6282","observed_orcids":["https://orcid.org/0000-0002-0397-6282"]},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Khalilipour, Alireza","raw_affiliation_strings":["Department of Computer Science , University of Antwerp , Antwerp , Belgium ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Antwerp , Antwerp , Belgium ;","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116424998","display_name":"Masoud Nasiripour","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210107186","display_name":"Hamedan University of Technology","ror":"https://ror.org/01hgb6e08","country_code":"IR","type":"education","lineage":["https://openalex.org/I4210107186"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Nasiripour, Masoud","raw_affiliation_strings":["Department of Computer Engineering , Hamedan University of Technology , Hamedan , Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering , Hamedan University of Technology , Hamedan , Iran","institution_ids":["https://openalex.org/I4210107186"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006565100","display_name":"Moharram Challenger","orcid":"https://orcid.org/0000-0002-5436-6070","observed_orcids":["https://orcid.org/0000-0002-5436-6070"]},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Challenger, Moharram","raw_affiliation_strings":["Department of Computer Science , University of Antwerp , Antwerp , Belgium ;","Flanders Make Strategic Research Center , Antwerp , Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Antwerp , Antwerp , Belgium ;","institution_ids":["https://openalex.org/I149213910"]},{"raw_affiliation_string":"Flanders Make Strategic Research Center , Antwerp , Belgium","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10028","display_name":"Topic Modeling","score":0.9672999978065491,"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":0.9672999978065491,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.01600000075995922,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.005100000184029341,"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/instruction-tuning-dataset","display_name":"instruction-tuning dataset","score":0.9100000262260437},{"id":"https://openalex.org/keywords/question-answering-dataset","display_name":"question answering dataset","score":0.75},{"id":"https://openalex.org/keywords/semantic-search","display_name":"semantic search","score":0.5899999737739563},{"id":"https://openalex.org/keywords/multi-document-question-answering","display_name":"multi-document question answering","score":0.703000009059906},{"id":"https://openalex.org/keywords/knowledge-forgetting","display_name":"knowledge forgetting","score":0.6430000066757202}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7817999720573425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.739799976348877},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7289999723434448},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.5548999905586243},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5521000027656555},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5192000269889832},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.382099986076355},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3125999867916107},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2957000136375427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28850001096725464},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.25}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.22817","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22817","pdf_url":"https://arxiv.org/pdf/2608.22817","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.2608.22817","doi":"https://doi.org/10.48550/arxiv.2608.22817","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22817","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:2608.22817","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22817","pdf_url":"https://arxiv.org/pdf/2608.22817","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":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320319799","display_name":"Flanders Make","ror":"https://ror.org/02ndjfz59"},{"id":"https://openalex.org/F4320323340","display_name":"Hamedan University of Technology","ror":"https://ror.org/01hgb6e08"},{"id":"https://openalex.org/F4320324595","display_name":"Universiteit Antwerpen","ror":"https://ror.org/008x57b05"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204180116.pdf","grobid_xml":"https://content.openalex.org/works/W7204180116.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2593864460","https://openalex.org/W2889787757","https://openalex.org/W3083410900","https://openalex.org/W4384918448","https://openalex.org/W4397028161","https://openalex.org/W4401043213","https://openalex.org/W4402660140","https://openalex.org/W4404650154","https://openalex.org/W4404869895","https://openalex.org/W4405766390","https://openalex.org/W4406500113","https://openalex.org/W4410061981","https://openalex.org/W4413145313","https://openalex.org/W4414019658","https://openalex.org/W4414037010","https://openalex.org/W4414939355","https://openalex.org/W4415124431","https://openalex.org/W4415330695","https://openalex.org/W4416072274","https://openalex.org/W7133233472","https://openalex.org/W7154621608"],"related_works":["https://openalex.org/W7204886693","https://openalex.org/W4399795632","https://openalex.org/W7147449069","https://openalex.org/W7221145854","https://openalex.org/W7171540796","https://openalex.org/W4412944217","https://openalex.org/W7171656061","https://openalex.org/W7202060095","https://openalex.org/W7154597927","https://openalex.org/W4416037429"],"abstract_inverted_index":{"Industrial":[0],"technical":[1,62],"reports":[2,63],"contain":[3],"high-value":[4],"knowledge":[5],"for":[6,228],"maintenance,":[7],"troubleshooting,":[8],"and":[9,25,31,34,64,88,123,142,169,195,235,246],"product":[10],"engineering,":[11],"but":[12,224],"their":[13],"heterogeneous":[14],"structure":[15],"(dense":[16],"prose,":[17],"specifications,":[18],"tables)":[19],"makes":[20],"them":[21],"difficult":[22],"to":[23,140,146],"index":[24],"reason":[26],"over":[27],"with":[28,50,120,164,171],"standard":[29],"retrieval":[30,86],"QA":[32,56,91,118],"pipelines,":[33],"no":[35],"public":[36,74],"instruction-tuning":[37],"or":[38],"benchmark":[39,126],"datasets":[40,57,234],"are":[41],"built":[42,58,157],"from":[43,59,138,144,249],"such":[44],"documents.":[45],"We":[46,152],"address":[47],"this":[48],"gap":[49],"Industrial-Instruction,":[51],"contributing":[52],"(i)":[53],"two":[54,154,201],"open":[55,130],"real":[60],"industrial":[61,244],"(ii)":[65],"the":[66,149,159,165,172,213,229],"end-to-end":[67],"pipeline":[68,236],"that":[69],"produces":[70],"them.":[71],"Using":[72],"906":[73],"Panasonic":[75,150],"documents":[76,122],"(7,525":[77],"pages),":[78],"we":[79],"apply":[80],"layout-aware":[81],"extraction,":[82],"build":[83],"a":[84,124,178,191,222,238],"semantic":[85],"index,":[87],"synthesize":[89],"multiple-choice":[90],"grounded":[92],"in":[93],"retrieved":[94],"evidence":[95],"under":[96],"five":[97],"query-document":[98],"relationships":[99],"(irrelevant":[100],"retrieval,":[101],"single-/multi-document":[102,104],"support,":[103],"answer).":[105],"After":[106],"filtering":[107],"an":[108],"initial":[109],"23.9k":[110],"generated":[111,163],"samples,":[112],"each":[113],"dataset":[114,189],"provides":[115],"approximately":[116],"13.6k":[117],"pairs":[119],"source":[121],"held-out":[125],"split.":[127],"Fine-tuning":[128],"small":[129,223],"LLMs":[131],"(under":[132],"10B":[133],"parameters)":[134],"improves":[135],"Set-Match":[136],"Accuracy":[137],"28.5%":[139],"42.0%":[141],"F1":[143],"46.6%":[145],"63.5%":[147],"on":[148,212],"benchmark.":[151],"release":[153],"parallel":[155],"versions":[156],"by":[158],"same":[160],"pipeline:":[161],"one":[162,170],"open-weight":[166],"Qwen3-30B-A3B-Instruct":[167],"model":[168],"closed,":[173],"API-based":[174],"Claude-Opus-4.6":[175,188,214],"model,":[176],"enabling":[177],"direct":[179],"comparison":[180],"of":[181,203],"open-":[182],"versus":[183,221],"frontier-model":[184],"data":[185,215,248],"generation.":[186],"The":[187],"yields":[190],"cleaner":[192],"raw":[193],"corpus":[194],"larger":[196],"fine-tuning":[197],"gains,":[198],"at":[199],"roughly":[200],"orders":[202],"magnitude":[204],"higher":[205],"cost.":[206],"MMLU":[207],"evaluation":[208],"shows":[209],"models":[210],"trained":[211],"retain":[216],"essentially":[217],"all":[218],"general":[219],"knowledge,":[220],"measurable":[225],"forgetting":[226],"effect":[227],"Qwen-generated":[230],"data.":[231],"Together,":[232],"these":[233],"offer":[237],"practical,":[239],"reproducible":[240],"path":[241],"toward":[242],"scalable":[243],"benchmarks":[245],"training":[247],"real-world":[250],"documentation.":[251]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-26T00:00:00"}