{"id":"https://openalex.org/W4413268030","doi":"https://doi.org/10.1145/3696630.3728538","title":"An Empirical Study of Issues in Large Language Model Training Systems","display_name":"An Empirical Study of Issues in Large Language Model Training Systems","publication_year":2025,"publication_date":"2025-06-23","ids":{"openalex":"https://openalex.org/W4413268030","doi":"https://doi.org/10.1145/3696630.3728538"},"language":"en","primary_location":{"id":"doi:10.1145/3696630.3728538","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3696630.3728538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering","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/A5031774552","display_name":"Yanjie Gao","orcid":"https://orcid.org/0000-0003-1899-8561"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanjie Gao","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1899-8561","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101745966","display_name":"Ruiming Lu","orcid":"https://orcid.org/0000-0002-4236-289X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiming Lu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4236-289X","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013547786","display_name":"Haoxiang Lin","orcid":"https://orcid.org/0000-0002-9148-5861"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoxiang Lin","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9148-5861","affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040815903","display_name":"Yueguo Chen","orcid":"https://orcid.org/0000-0002-2239-4472"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueguo Chen","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2239-4472","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031774552"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10349303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"122","last_page":"133"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T12031","display_name":"Speech and dialogue systems","score":0.9836999773979187,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7665896415710449},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.4536222815513611},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.43957021832466125},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.41066187620162964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3507375121116638},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3419427275657654},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.24988046288490295},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08058103919029236},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0696001946926117}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7665896415710449},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.4536222815513611},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.43957021832466125},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.41066187620162964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3507375121116638},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3419427275657654},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.24988046288490295},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08058103919029236},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0696001946926117},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3696630.3728538","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3696630.3728538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1506512744","https://openalex.org/W1522301498","https://openalex.org/W2002011878","https://openalex.org/W2053154970","https://openalex.org/W2968594320","https://openalex.org/W2973727699","https://openalex.org/W3047908100","https://openalex.org/W3109716606","https://openalex.org/W3155806510","https://openalex.org/W4225847927","https://openalex.org/W4229701516","https://openalex.org/W4238124605","https://openalex.org/W4253752119","https://openalex.org/W4255108598","https://openalex.org/W4285225959","https://openalex.org/W4292779060","https://openalex.org/W4320005767","https://openalex.org/W4327594616","https://openalex.org/W4376505605","https://openalex.org/W4382322281","https://openalex.org/W4387596640","https://openalex.org/W4388979610","https://openalex.org/W4389519070","https://openalex.org/W4391983842","https://openalex.org/W4405562048","https://openalex.org/W6637031373","https://openalex.org/W6778883912","https://openalex.org/W6791858558","https://openalex.org/W6864014924"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W4412817058","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,22],"(LLMs)":[3],"have":[4],"gained":[5],"significant":[6],"traction":[7],"in":[8,13,44],"recent":[9],"years,":[10],"driving":[11],"advancements":[12],"various":[14],"applications.":[15],"The":[16],"training":[17,28,46],"and":[18,38,59,66],"evaluation":[19],"of":[20],"these":[21],"depend":[23],"heavily":[24],"on":[25],"specialized":[26],"LLM":[27,45],"systems,":[29],"which":[30],"are":[31],"deployed":[32],"across":[33],"numerous":[34],"GPUs,":[35],"partition":[36],"LLMs,":[37],"process":[39],"large":[40],"datasets.":[41],"However,":[42],"issues":[43],"systems":[47],"can":[48],"lead":[49],"to":[50],"program":[51],"crashes":[52],"or":[53],"unexpected":[54],"behavior,":[55],"reducing":[56],"development":[57],"productivity":[58],"wasting":[60],"valuable":[61],"resources":[62],"such":[63],"as":[64],"GPUs":[65],"storage.":[67]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}