{"id":"https://openalex.org/W4412888933","doi":"https://doi.org/10.18653/v1/2025.findings-acl.39","title":"Comparing Bad Apples to Good Oranges Aligning Large Language Models via Joint Preference Optimization","display_name":"Comparing Bad Apples to Good Oranges Aligning Large Language Models via Joint Preference Optimization","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888933","doi":"https://doi.org/10.18653/v1/2025.findings-acl.39"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.39","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.39","pdf_url":"https://aclanthology.org/2025.findings-acl.39.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.39.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112428050","display_name":"Hritik Bansal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hritik Bansal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027401438","display_name":"Ashima Suvarna","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashima Suvarna","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028997209","display_name":"Gantavya Bhatt","orcid":"https://orcid.org/0009-0003-2338-1598"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gantavya Bhatt","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030248499","display_name":"Nanyun Peng","orcid":"https://orcid.org/0000-0002-8509-6595"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nanyun Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087096372","display_name":"Kai-Wei Chang","orcid":"https://orcid.org/0000-0001-5365-0072"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai-Wei Chang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5014409944","display_name":"Aditya Grover","orcid":"https://orcid.org/0000-0002-4217-6624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aditya Grover","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":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"701","last_page":"723"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.6032999753952026,"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":0.6032999753952026,"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/preference","display_name":"Preference","score":0.6913723945617676},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6366046667098999},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5887256264686584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36709147691726685},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1574077010154724},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1263420283794403},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11741787195205688}],"concepts":[{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.6913723945617676},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6366046667098999},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5887256264686584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36709147691726685},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1574077010154724},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1263420283794403},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11741787195205688},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.39","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.39","pdf_url":"https://aclanthology.org/2025.findings-acl.39.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.39","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.39","pdf_url":"https://aclanthology.org/2025.findings-acl.39.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888933.pdf","grobid_xml":"https://content.openalex.org/works/W4412888933.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"A":[0],"common":[1],"technique":[2],"for":[3,86,137],"aligning":[4],"large":[5],"language":[6],"models":[7],"(LLMs)":[8],"relies":[9,25],"on":[10,19,27,72],"acquiring":[11],"human":[12,54,168],"preferences":[13,43,74,148],"by":[14,132,161],"comparing":[15],"multiple":[16],"generations":[17,32],"conditioned":[18],"a":[20,68,98,164,178,187,205],"fixed":[21],"context.This":[22],"method,":[23],"however,":[24],"solely":[26],"pairwise":[28],"comparisons,":[29],"where":[30],"the":[31,48,60,77,105,109,114,157],"are":[33,84],"evaluated":[34],"within":[35],"an":[36],"identical":[37],"context.While":[38],"effective":[39],"to":[40,46],"such":[41],"conditional":[42,87],"often":[44],"fail":[45],"encompass":[47],"nuanced":[49],"and":[50,66,134,139,151,172],"multidimensional":[51],"nature":[52],"of":[53,63,108,159,167,180,189,207],"preferences.In":[55],"this":[56],"work,":[57],"we":[58,92],"revisit":[59],"traditional":[61],"paradigm":[62],"preference":[64,81,100,123,169],"acquisition":[65],"propose":[67,93],"new":[69,99],"axis":[70],"based":[71],"eliciting":[73],"jointly":[75],"over":[76,113,149],"instructionresponse":[78,111,116],"pairs.Unlike":[79],"prior":[80],"optimizations,":[82],"which":[83],"designed":[85],"ranking":[88],"protocols":[89],"(e.g.,":[90],"DPO),":[91],"Joint":[94],"Preference":[95],"Optimization":[96],"(JPO),":[97],"optimization":[101],"objective":[102],"that":[103,146],"upweights":[104],"joint":[106,121,147],"probability":[107],"chosen":[110],"pair":[112],"rejected":[115],"pair.Interestingly,":[117],"LLMs":[118,160],"trained":[119,129],"with":[120,130],"instruction-response":[122],"data":[124,171],"using":[125],"JPO":[126],"outperform":[127],"LLM":[128],"DPO":[131],"5.2%":[133],"3.3%":[135],"win-rate":[136],"summarization":[138],"open-ended":[140],"dialogue":[141],"datasets,":[142],"respectively.Our":[143],"findings":[144],"reveal":[145],"instruction":[150],"response":[152],"pairs":[153],"can":[154],"significantly":[155],"enhance":[156],"alignment":[158],"tapping":[162],"into":[163],"broader":[165],"spectrum":[166],"elicitation.The":[170],"code":[173],"is":[174],"available":[175],"at":[176],"https://github.com/Hritikbansal/jpo.Create":[177],"list":[179,188,206],"four":[181,190],"fruits":[182,191],"other":[183],"than":[184],"Apple":[185],"Create":[186,204],"Apple,":[192,200],"Orange,":[193,196,201],"Banana,":[194,202],"Grape":[195,203],"Blueberry,":[197],"Kiwi,":[198],"Banana":[199],"beach":[208],"activities":[209],"wear":[210],"sunscreen,":[211],"don't":[212],"litter":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}