{"id":"https://openalex.org/W7126414014","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.39","title":"Personalized Abstractive Summarization by Tri-agent Generation Pipeline","display_name":"Personalized Abstractive Summarization by Tri-agent Generation Pipeline","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126414014","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.39"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.39","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.39","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.39","pdf_url":"https://aclanthology.org/2024.findings-eacl.39.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2024.findings-eacl.39.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124670536","display_name":"Wen Xiao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Wen Xiao","raw_affiliation_strings":["Microsoft Azure AI","University of British Columbia , Vancouver , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Azure AI","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"University of British Columbia , Vancouver , Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124483234","display_name":"Yujia Xie","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yujia Xie","raw_affiliation_strings":["Microsoft Azure AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Azure AI","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049259877","display_name":"Giuseppe Carenini","orcid":"https://orcid.org/0000-0003-4310-0119","observed_orcids":["https://orcid.org/0000-0003-4310-0119"]},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Giuseppe Carenini","raw_affiliation_strings":["University of British Columbia , Vancouver , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of British Columbia , Vancouver , Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125128722","display_name":"Pengcheng He","orcid":"https://orcid.org/0009-0002-3110-8797","observed_orcids":["https://orcid.org/0009-0002-3110-8797"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pengcheng He","raw_affiliation_strings":["Microsoft Azure AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Azure AI","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8662,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77335348,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"570","last_page":"581"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.801800012588501,"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":0.801800012588501,"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":0.0754999965429306,"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":0.016599999740719795,"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/personalized-summarization","display_name":"personalized summarization","score":0.8080000281333923},{"id":"https://openalex.org/keywords/abstractive-summarization","display_name":"abstractive summarization","score":0.9940000176429749},{"id":"https://openalex.org/keywords/user-preference-alignment","display_name":"user preference alignment","score":0.5440000295639038},{"id":"https://openalex.org/keywords/instruction-generation","display_name":"instruction generation","score":0.6710000038146973},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6919999718666077},{"id":"https://openalex.org/keywords/chatgpt","display_name":"ChatGPT","score":0.8180000185966492}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7003999948501587},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6829000115394592},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6783999800682068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5425999760627747},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41179999709129333},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2540999948978424},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2533999979496002}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.39","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.39","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.39","pdf_url":"https://aclanthology.org/2024.findings-eacl.39.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2305.02483","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.02483","pdf_url":"https://arxiv.org/pdf/2305.02483","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2305.02483","doi":"https://doi.org/10.48550/arxiv.2305.02483","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.02483","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.39","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.39","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.39","pdf_url":"https://aclanthology.org/2024.findings-eacl.39.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126414014.pdf","grobid_xml":"https://content.openalex.org/works/W7126414014.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416054679","https://openalex.org/W4412945169","https://openalex.org/W4412888078","https://openalex.org/W4401042707","https://openalex.org/W4402351528","https://openalex.org/W7108225583","https://openalex.org/W4404783018","https://openalex.org/W4389519289","https://openalex.org/W4415330372","https://openalex.org/W7111394825"],"abstract_inverted_index":{"Tailoring":[0],"outputs":[1,122],"from":[2,99],"large":[3,67],"language":[4,68],"models,":[5],"like":[6],"ChatGPT,":[7],"to":[8,36,61,86,104],"implicit":[9],"user":[10,53,126],"preferences":[11],"remains":[12],"a":[13,24,29,79,100],"challenge":[14],"despite":[15],"their":[16],"impressive":[17],"generative":[18],"capabilities.In":[19],"this":[20],"paper,":[21],"we":[22],"propose":[23],"tri-agent":[25],"generation":[26],"pipeline":[27],"comprising":[28],"generator,":[30],"an":[31,34,42],"instructor,":[32],"and":[33,55,76],"editor":[35,57,102],"enhance":[37],"output":[38,60,88],"personalization.The":[39],"generator":[40,75],"produces":[41],"initial":[43],"output,":[44],"the":[45,56,59,74,84,91,115],"instructor":[46,85,92],"automatically":[47],"generates":[48],"editing":[49],"instructions":[50],"based":[51],"on":[52,109],"preferences,":[54],"refines":[58],"align":[62],"with":[63,78],"those":[64],"preferences.The":[65],"inferenceonly":[66],"model":[69,81,103],"(ChatGPT)":[70],"serves":[71],"as":[72,83],"both":[73],"editor,":[77],"smaller":[80],"acting":[82],"guide":[87],"generation.We":[89],"train":[90],"using":[93],"editorsteered":[94],"reinforcement":[95],"learning,":[96],"leveraging":[97],"feedback":[98],"large-scale":[101],"optimize":[105],"instruction":[106],"generation.Experimental":[107],"results":[108],"two":[110],"abstractive":[111],"summarization":[112],"datasets":[113],"demonstrate":[114],"effectiveness":[116],"of":[117],"our":[118],"approach":[119],"in":[120],"generating":[121],"that":[123],"better":[124],"meet":[125],"expectations.1":[127]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2026-02-02T00:00:00"}