{"id":"https://openalex.org/W4412886772","doi":"https://doi.org/10.18653/v1/2025.acl-long.105","title":"Exploring Forgetting in Large Language Model Pre-Training","display_name":"Exploring Forgetting in Large Language Model Pre-Training","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886772","doi":"https://doi.org/10.18653/v1/2025.acl-long.105"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.105","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.105","pdf_url":"https://aclanthology.org/2025.acl-long.105.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.105.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chonghua Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chonghua Liao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101577090","display_name":"Ruobing Xie","orcid":"https://orcid.org/0000-0003-3170-5647"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruobing Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039337290","display_name":"Xingwu Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingwu Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031953648","display_name":"Haowen Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haowen Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020128898","display_name":"Zhanhui Kang","orcid":"https://orcid.org/0009-0006-5151-4222"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhanhui Kang","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":1.673,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83259684,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2112","last_page":"2127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9671000242233276,"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":0.9671000242233276,"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":0.9524999856948853,"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":0.7329792976379395},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.7223866581916809},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.46039125323295593},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45464807748794556},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44493523240089417},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42411869764328003},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.17300763726234436},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14013755321502686}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7329792976379395},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.7223866581916809},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.46039125323295593},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45464807748794556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44493523240089417},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42411869764328003},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.17300763726234436},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14013755321502686},{"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:10.18653/v1/2025.acl-long.105","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.105","pdf_url":"https://aclanthology.org/2025.acl-long.105.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.105","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.105","pdf_url":"https://aclanthology.org/2025.acl-long.105.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":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412886772.pdf","grobid_xml":"https://content.openalex.org/works/W4412886772.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4289718052","https://openalex.org/W2164121020","https://openalex.org/W2145559838","https://openalex.org/W2905319430","https://openalex.org/W3116498279","https://openalex.org/W4287549553","https://openalex.org/W4310285384","https://openalex.org/W3183027292","https://openalex.org/W4248896073","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Catastrophic":[0],"forgetting":[1,21,30,40,65,74,97],"remains":[2],"a":[3],"formidable":[4],"obstacle":[5],"to":[6,54,72],"building":[7],"an":[8],"omniscient":[9],"model":[10],"in":[11,22,41],"large":[12],"language":[13],"models":[14],"(LLMs).Despite":[15],"the":[16,35,76,83,89],"pioneering":[17],"research":[18,103],"on":[19,29,60,96,104],"task-level":[20],"LLM":[23],"fine-tuning,":[24],"there":[25],"is":[26],"scant":[27],"focus":[28],"during":[31,75],"pre-training.We":[32],"systematically":[33],"explored":[34,68],"existence":[36],"and":[37,50,94],"measurement":[38],"of":[39,64,91,98],"pre-training,":[42],"questioning":[43],"traditional":[44],"metrics":[45,53],"such":[46],"as":[47],"perplexity":[48],"(PPL)":[49],"introducing":[51],"new":[52],"better":[55],"detect":[56],"entity":[57],"memory":[58],"retention.Based":[59],"our":[61],"revised":[62],"assessment":[63],"metrics,":[66],"we":[67,80],"low-cost,":[69],"straightforward":[70],"methods":[71],"mitigate":[73],"pre-training":[77,99],"phase.In":[78],"addition,":[79],"carefully":[81],"analyzed":[82],"learning":[84],"curves,":[85],"offering":[86],"insights":[87],"into":[88],"dynamics":[90],"forgetting.Extensive":[92],"evaluations":[93],"analyses":[95],"could":[100],"facilitate":[101],"future":[102],"LLMs.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}