{"id":"https://openalex.org/W7166822351","doi":"https://doi.org/10.18653/v1/2026.acl-long.999","title":"Perplexity-Aware Data Scaling Law: Perplexity Landscapes Predict Performance for Continual Pre-training","display_name":"Perplexity-Aware Data Scaling Law: Perplexity Landscapes Predict Performance for Continual Pre-training","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166822351","doi":"https://doi.org/10.18653/v1/2026.acl-long.999"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.999","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.999","pdf_url":"https://aclanthology.org/2026.acl-long.999.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 64th 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/2026.acl-long.999.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139840670","display_name":"Lei Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139759003","display_name":"Hao Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139737529","display_name":"Xiaoyan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoyan Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139798382","display_name":"Yue Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139819426","display_name":"Zhixuan Chu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhixuan Chu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139812884","display_name":"Jian Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139790357","display_name":"Jinjie Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinjie Gu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139800250","display_name":"Kui Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kui Ren","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81181509,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21889","last_page":"21901"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1437000036239624,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1437000036239624,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.06509999930858612,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.05609999969601631,"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/perplexity","display_name":"Perplexity","score":0.8669999837875366},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.3725000023841858},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.37059998512268066},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.31859999895095825},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.30640000104904175}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.8669999837875366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5871999859809875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5160999894142151},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43320000171661377},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3312000036239624},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3147999942302704},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.999","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.999","pdf_url":"https://aclanthology.org/2026.acl-long.999.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.999","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.999","pdf_url":"https://aclanthology.org/2026.acl-long.999.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5973436832427979,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320318398","display_name":"Ant Group","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166822351.pdf","grobid_xml":"https://content.openalex.org/works/W7166822351.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Lei":[0],"Liu,":[1],"Hao":[2],"Zhu,":[3],"Xiaoyan":[4],"Yang,":[5],"Yue":[6],"Shen,":[7],"Zhixuan":[8],"Chu,":[9],"Jian":[10],"Wang,":[11],"Jinjie":[12],"Gu,":[13],"Kui":[14],"Ren.":[15],"Proceedings":[16],"of":[17,22],"the":[18,23],"64th":[19],"Annual":[20],"Meeting":[21],"Association":[24],"for":[25],"Computational":[26],"Linguistics":[27],"(Volume":[28],"1:":[29],"Long":[30],"Papers).":[31],"2026.":[32]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}