{"id":"https://openalex.org/W4412886668","doi":"https://doi.org/10.18653/v1/2025.acl-long.249","title":"Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models","display_name":"Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886668","doi":"https://doi.org/10.18653/v1/2025.acl-long.249"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.249","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.249","pdf_url":"https://aclanthology.org/2025.acl-long.249.pdf","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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.249.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111322472","display_name":"Zihan Qiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zihan Qiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101982557","display_name":"Zeyu Huang","orcid":"https://orcid.org/0000-0002-8117-3231"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeyu Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073856221","display_name":"Bo Zheng","orcid":"https://orcid.org/0000-0002-4037-6315"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116000564","display_name":"Kaiyue Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaiyue Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027950866","display_name":"Z. Y. Wang","orcid":"https://orcid.org/0009-0008-3278-319X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zekun Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004626105","display_name":"Rui Men","orcid":"https://orcid.org/0000-0002-4429-3461"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Men","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086717154","display_name":"Ivan Titov","orcid":"https://orcid.org/0000-0002-2583-1893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivan Titov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062188134","display_name":"Dayiheng Liu","orcid":"https://orcid.org/0000-0002-8755-8941"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dayiheng Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101794174","display_name":"Jingren Zhou","orcid":"https://orcid.org/0000-0002-7159-901X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingren Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100612233","display_name":"Junyang Lin","orcid":"https://orcid.org/0000-0001-9931-383X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junyang Lin","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":17.5129,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.99241387,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5005","last_page":"5018"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9239000082015991,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9024999737739563,"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/training","display_name":"Training (meteorology)","score":0.7288123965263367},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6926198601722717}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7288123965263367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6926198601722717},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.249","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.249","pdf_url":"https://aclanthology.org/2025.acl-long.249.pdf","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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.249","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.249","pdf_url":"https://aclanthology.org/2025.acl-long.249.pdf","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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412886668.pdf","grobid_xml":"https://content.openalex.org/works/W4412886668.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659"],"abstract_inverted_index":{"Zihan":[0],"Qiu,":[1],"Zeyu":[2],"Huang,":[3],"Bo":[4],"Zheng,":[5],"Kaiyue":[6],"Wen,":[7],"Zekun":[8],"Wang,":[9],"Rui":[10],"Men,":[11],"Ivan":[12],"Titov,":[13],"Dayiheng":[14],"Liu,":[15],"Jingren":[16],"Zhou,":[17],"Junyang":[18],"Lin.":[19],"Proceedings":[20],"of":[21,26],"the":[22,27],"63rd":[23],"Annual":[24],"Meeting":[25],"Association":[28],"for":[29],"Computational":[30],"Linguistics":[31],"(Volume":[32],"1:":[33],"Long":[34],"Papers).":[35],"2025.":[36]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
