{"id":"https://openalex.org/W4412889783","doi":"https://doi.org/10.18653/v1/2025.acl-long.1366","title":"Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning","display_name":"Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889783","doi":"https://doi.org/10.18653/v1/2025.acl-long.1366"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1366","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1366","pdf_url":"https://aclanthology.org/2025.acl-long.1366.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.1366.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103564790","display_name":"Andrei Mircea","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrei Mircea","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Supriyo Chakraborty","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Supriyo Chakraborty","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119181871","display_name":"Nima Chitsazan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nima Chitsazan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055430458","display_name":"Irina Rish","orcid":"https://orcid.org/0000-0001-6856-5057"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Irina Rish","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5119181872","display_name":"Ekaterina Lobacheva","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ekaterina Lobacheva","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08701065,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"28154","last_page":"28188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8824999928474426,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.8824999928474426,"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/T10028","display_name":"Topic Modeling","score":0.859000027179718,"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/zero","display_name":"Zero (linguistics)","score":0.746178388595581},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.6328260898590088},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5744691491127014},{"id":"https://openalex.org/keywords/scaling-law","display_name":"Scaling law","score":0.5613954067230225},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5522246956825256},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2279377281665802},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.14936187863349915}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.746178388595581},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.6328260898590088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5744691491127014},{"id":"https://openalex.org/C2988430800","wikidata":"https://www.wikidata.org/wiki/Q428971","display_name":"Scaling law","level":3,"score":0.5613954067230225},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5522246956825256},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2279377281665802},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.14936187863349915},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1366","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1366","pdf_url":"https://aclanthology.org/2025.acl-long.1366.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.1366","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1366","pdf_url":"https://aclanthology.org/2025.acl-long.1366.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":[{"display_name":"Quality Education","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889783.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2117748264","https://openalex.org/W4298190863","https://openalex.org/W2518229301","https://openalex.org/W2597205018","https://openalex.org/W2554072523","https://openalex.org/W1671671741","https://openalex.org/W2952002823","https://openalex.org/W2013329450","https://openalex.org/W2140409554","https://openalex.org/W3104909087"],"abstract_inverted_index":{"Andrei":[0],"Mircea,":[1],"Supriyo":[2],"Chakraborty,":[3],"Nima":[4],"Chitsazan,":[5],"Irina":[6],"Rish,":[7],"Ekaterina":[8],"Lobacheva.":[9],"Proceedings":[10],"of":[11,16],"the":[12,17],"63rd":[13],"Annual":[14],"Meeting":[15],"Association":[18],"for":[19],"Computational":[20],"Linguistics":[21],"(Volume":[22],"1:":[23],"Long":[24],"Papers).":[25],"2025.":[26]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
