{"id":"https://openalex.org/W4416036283","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.737","title":"Tuning Less, Prompting More: In-Context Preference Learning Pipeline for Natural Language Transformation","display_name":"Tuning Less, Prompting More: In-Context Preference Learning Pipeline for Natural Language Transformation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036283","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.737"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.737","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.737","pdf_url":"https://aclanthology.org/2025.emnlp-main.737.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.737.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039799143","display_name":"Shuyun Yang","orcid":"https://orcid.org/0000-0002-0833-8896"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shuyun Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456303","display_name":"Yan Zhang","orcid":"https://orcid.org/0000-0002-7329-0382"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017838982","display_name":"Zhengmao Ye","orcid":"https://orcid.org/0000-0002-2638-9750"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengmao Ye","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103153652","display_name":"Lei Duan","orcid":"https://orcid.org/0000-0001-7254-1832"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Duan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102006509","display_name":"Mingjie Tang","orcid":"https://orcid.org/0009-0008-5012-5035"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingjie Tang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039799143"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17328975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14587","last_page":"14598"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2012999951839447,"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":0.2012999951839447,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1281999945640564,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.12700000405311584,"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/pipeline","display_name":"Pipeline (software)","score":0.6079999804496765},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4779999852180481},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.45100000500679016},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4108000099658966},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.3474999964237213},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.31349998712539673}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6344000101089478},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6079999804496765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5985999703407288},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4779999852180481},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46239998936653137},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.45100000500679016},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4108000099658966},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26829999685287476},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.737","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.737","pdf_url":"https://aclanthology.org/2025.emnlp-main.737.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.737","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.737","pdf_url":"https://aclanthology.org/2025.emnlp-main.737.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1547855224","display_name":null,"funder_award_id":"2024ZD0607700","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G37568934","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5450352184","display_name":null,"funder_award_id":"92470204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7603945087","display_name":null,"funder_award_id":"62472294","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036283.pdf","grobid_xml":"https://content.openalex.org/works/W4416036283.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Natural":[0],"language":[1],"transformation":[2],"(NLT)":[3],"tasks,":[4,129],"such":[5,109],"as":[6,110],"machine":[7],"translation":[8],"(MT)":[9],"and":[10,20,38,84,96,119,127],"text":[11],"style":[12],"transfer":[13],"(TST),":[14],"require":[15],"models":[16,37,68],"to":[17,79],"generate":[18],"accurate":[19],"contextually":[21],"appropriate":[22],"outputs.However,":[23],"existing":[24,107],"approaches":[25],"face":[26],"significant":[27],"challenges,":[28],"including":[29],"the":[30,39,56,61,77],"computational":[31],"costs":[32],"of":[33,43,58,63],"leveraging":[34],"large":[35],"pre-trained":[36],"limited":[40],"generalization":[41],"ability":[42],"finetuned":[44],"smaller":[45,67],"models.In":[46],"this":[47],"paper,":[48],"we":[49],"propose":[50],"a":[51,131],"novel":[52],"framework":[53],"that":[54,103],"combines":[55],"flexibility":[57],"prompting":[59],"with":[60,86],"cost-effectiveness":[62],"fine-tuning.Our":[64],"method":[65],"enhances":[66],"by":[69],"integrating":[70],"In-Context":[71],"Examples":[72],"(ICE)":[73],"from":[74],"retrieval,":[75],"enabling":[76],"model":[78],"better":[80],"capture":[81],"contextual":[82],"information":[83],"align":[85],"userlevel":[87],"preferences.We":[88],"further":[89],"improve":[90],"performance":[91],"through":[92],"hierarchical":[93],"contrastive":[94],"learning":[95],"dynamic":[97],"preference":[98],"inference":[99],"mechanisms.Experimental":[100],"results":[101],"demonstrate":[102],"our":[104],"approach":[105],"outperforms":[106],"methods,":[108],"Supervised":[111],"Fine":[112],"Tuning":[113],"(SFT),":[114],"Direct":[115],"Preference":[116,121],"Optimization":[117,122],"(DPO),":[118],"Contrastive":[120],"(CPO),":[123],"across":[124],"both":[125],"MT":[126],"TST":[128],"providing":[130],"more":[132],"efficient":[133],"solution":[134],"for":[135],"resource-constrained":[136],"environments.":[137]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-11-08T00:00:00"}