{"id":"https://openalex.org/W7127045794","doi":"https://doi.org/10.1145/3784833.3784879","title":"Industrial-Scale Data Processing and LLM Evaluation for Coal Mine Safety","display_name":"Industrial-Scale Data Processing and LLM Evaluation for Coal Mine Safety","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7127045794","doi":"https://doi.org/10.1145/3784833.3784879"},"language":null,"primary_location":{"id":"doi:10.1145/3784833.3784879","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784833.3784879","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 11th International Conference on Communication and Information Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3784833.3784879","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124724316","display_name":"Meng Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Meng Yang","raw_affiliation_strings":["School of Artificial Intelligence, China University of Mining and Technology (Beijing), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4693-4402","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, China University of Mining and Technology (Beijing), Beijing, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124730976","display_name":"Chuanrui Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanrui Cui","raw_affiliation_strings":["School of Artificial Intelligence, China University of Mining and Technology (Beijing), Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-8019-8779","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, China University of Mining and Technology (Beijing), Beijing, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124746401","display_name":"Yanan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanan Li","raw_affiliation_strings":["School of Artificial Intelligence, China University of Mining and Technology (Beijing), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1990-8994","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, China University of Mining and Technology (Beijing), Beijing, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124696530","display_name":"Ning Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210166112","display_name":"State Key Laboratory of Remote Sensing Science","ror":"https://ror.org/05wzjqa24","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210166112"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Chen","raw_affiliation_strings":["Institute of Remote Sensing and Geographic Information Systems, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-8424-302X","affiliations":[{"raw_affiliation_string":"Institute of Remote Sensing and Geographic Information Systems, Peking University, Beijing, China","institution_ids":["https://openalex.org/I4210166112","https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124702762","display_name":"Pengpeng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengpeng Zhang","raw_affiliation_strings":["Artificial Intelligence Research Institute, Beijing LongRuan Technologies Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5397-1017","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute, Beijing LongRuan Technologies Inc., Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5124724316"],"corresponding_institution_ids":["https://openalex.org/I25757504"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.70673175,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"554","last_page":"562"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10809","display_name":"Occupational Health and Safety Research","score":0.5228000283241272,"subfield":{"id":"https://openalex.org/subfields/3614","display_name":"Radiological and Ultrasound Technology"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10809","display_name":"Occupational Health and Safety Research","score":0.5228000283241272,"subfield":{"id":"https://openalex.org/subfields/3614","display_name":"Radiological and Ultrasound Technology"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.04520000144839287,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.03819999843835831,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/coal-mining","display_name":"Coal mining","score":0.6187999844551086},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6074000000953674},{"id":"https://openalex.org/keywords/safety-monitoring","display_name":"Safety monitoring","score":0.5249999761581421},{"id":"https://openalex.org/keywords/data-processing","display_name":"Data processing","score":0.4876999855041504},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4869999885559082},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48249998688697815},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4004000127315521},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.388700008392334},{"id":"https://openalex.org/keywords/complex-event-processing","display_name":"Complex event processing","score":0.38370001316070557},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3695000112056732}],"concepts":[{"id":"https://openalex.org/C108615695","wikidata":"https://www.wikidata.org/wiki/Q12880211","display_name":"Coal mining","level":3,"score":0.6187999844551086},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6074000000953674},{"id":"https://openalex.org/C2777488183","wikidata":"https://www.wikidata.org/wiki/Q6900510","display_name":"Safety monitoring","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.510200023651123},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.4876999855041504},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4869999885559082},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4828999936580658},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48249998688697815},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.388700008392334},{"id":"https://openalex.org/C123606473","wikidata":"https://www.wikidata.org/wiki/Q907918","display_name":"Complex event processing","level":3,"score":0.38370001316070557},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C33326189","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information integration","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.33079999685287476},{"id":"https://openalex.org/C2779141794","wikidata":"https://www.wikidata.org/wiki/Q12099081","display_name":"Mine safety","level":4,"score":0.32659998536109924},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.3163999915122986},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C87868495","wikidata":"https://www.wikidata.org/wiki/Q750843","display_name":"Information processing","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3070000112056732},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C71405471","wikidata":"https://www.wikidata.org/wiki/Q757012","display_name":"Quality management","level":3,"score":0.2535000145435333},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3784833.3784879","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784833.3784879","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 11th International Conference on Communication and Information Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3784833.3784879","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784833.3784879","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 11th International Conference on Communication and Information Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.47619083523750305}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2065071658","https://openalex.org/W3156789018","https://openalex.org/W4309674289","https://openalex.org/W4403451304","https://openalex.org/W4406617927","https://openalex.org/W4409348182"],"related_works":[],"abstract_inverted_index":{"Industrial":[0],"information":[1,168],"processing":[2,31,156],"in":[3,134,161],"safety-critical":[4],"domains":[5],"requires":[6],"the":[7,14,151],"integration":[8],"of":[9,16,70,141,153],"heterogeneous":[10],"data":[11,30,42,88,155],"sources":[12],"and":[13,46,64,73,83,111,122,139,157],"transformation":[15],"domain":[17,71],"expertise":[18],"into":[19],"actionable":[20],"knowledge.":[21],"To":[22,101],"address":[23],"these":[24],"challenges,":[25],"this":[26,55,87],"paper":[27],"proposes":[28],"a":[29,62,93,107],"framework":[32,115],"for":[33,49,96,166],"industrial":[34,167],"large":[35],"language":[36],"models":[37],"(LLMs)":[38],"that":[39,117,129],"standardizes":[40],"multisource":[41,63],"integration,":[43],"semantic":[44],"cleaning,":[45],"quality":[47],"monitoring":[48],"large-scale":[50],"model":[51],"training.":[52],"Based":[53],"on":[54],"framework,":[56],"we":[57,90,105],"construct":[58],"Mine":[59],"Safety":[60],"Intelligence(MSI),":[61],"multitask":[65],"corpus":[66],"containing":[67],"10":[68],"GB":[69],"text":[72],"10,000":[74],"high-quality":[75],"instruction\u2013response":[76],"pairs":[77],"covering":[78],"safety":[79,99,142],"regulations,":[80],"emergency":[81],"response,":[82],"risk":[84],"management.":[85],"Using":[86],"set,":[89],"develop":[91],"MS-GLM,":[92],"domain-adaptive":[94],"LLM":[95],"coal":[97],"mining":[98],"applications.":[100],"ensure":[102],"reliable":[103],"evaluation,":[104],"establish":[106],"dedicated":[108],"benchmark":[109],"(CMS-QED)":[110],"an":[112],"expert-driven":[113],"scoring":[114],"(CMS-QEM)":[116],"jointly":[118],"assess":[119],"accuracy,":[120,136],"interpretability,":[121],"user":[123],"experience.":[124],"The":[125],"experimental":[126],"results":[127],"demonstrate":[128],"MS-GLM":[130],"achieves":[131],"substantial":[132],"improvements":[133],"factual":[135],"reasoning":[137],"precision,":[138],"understanding":[140],"compliance":[143],"compared":[144],"to":[145],"baseline":[146],"models.":[147],"These":[148],"findings":[149],"highlight":[150],"effectiveness":[152],"structured":[154],"domain-aligned":[158],"evaluation":[159],"frameworks":[160],"advancing":[162],"intelligent":[163],"decision":[164],"support":[165],"systems.":[169]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-02-03T00:00:00"}