{"id":"https://openalex.org/W7166851334","doi":"https://doi.org/10.18653/v1/2026.findings-acl.185","title":"Intrinsic Mutual Information as a Modulator for Preference Optimization","display_name":"Intrinsic Mutual Information as a Modulator for Preference Optimization","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166851334","doi":"https://doi.org/10.18653/v1/2026.findings-acl.185"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.185","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.185","pdf_url":"https://aclanthology.org/2026.findings-acl.185.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 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.185.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139838340","display_name":"Peng Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Liao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134860670","display_name":"Peijia Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peijia Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139850441","display_name":"Lingbo Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingbo Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060335069","display_name":"Shangsong Liang","orcid":"https://orcid.org/0000-0003-1625-2168"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shangsong Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139726538","display_name":"Lin Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Chen","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":0.85761249,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3790","last_page":"3808"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.2727999985218048,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.2727999985218048,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10050","display_name":"Multi-Criteria Decision Making","score":0.027499999850988388,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.01899999938905239,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/mutual-information","display_name":"Mutual information","score":0.7135000228881836},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.4562999904155731},{"id":"https://openalex.org/keywords/complete-information","display_name":"Complete information","score":0.26759999990463257},{"id":"https://openalex.org/keywords/information-theory","display_name":"Information theory","score":0.2669000029563904},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.25940001010894775}],"concepts":[{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.7135000228881836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46470001339912415},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39160001277923584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3549000024795532},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25940001010894775},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C2983568541","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Information transmission","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.185","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.185","pdf_url":"https://aclanthology.org/2026.findings-acl.185.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 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.185","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.185","pdf_url":"https://aclanthology.org/2026.findings-acl.185.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 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G642842208","display_name":null,"funder_award_id":"W2512008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8062609164","display_name":null,"funder_award_id":"62272498","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G812025595","display_name":null,"funder_award_id":"62572500","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166851334.pdf","grobid_xml":"https://content.openalex.org/works/W7166851334.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Offline":[0],"preference":[1,73,88],"optimization":[2],"methods,":[3],"such":[4],"as":[5],"Direct":[6],"Preference":[7,81],"Optimization":[8,82],"(DPO),":[9],"offer":[10],"significant":[11],"advantages":[12],"in":[13,34,50],"aligning":[14],"Large":[15],"Language":[16],"Models":[17],"(LLMs)":[18],"with":[19,25,83],"human":[20],"values.However,":[21],"achieving":[22],"optimal":[23],"performance":[24,103],"these":[26,46],"methods":[27,47,106],"typically":[28],"involves":[29],"additional":[30,92],"hyperparameter":[31,59,84],"tuning,":[32],"resulting":[33],"substantial":[35],"time":[36],"overhead.Although":[37],"prior":[38],"work":[39],"has":[40],"proposed":[41],"a":[42,66],"range":[43],"of":[44],"improvements,":[45],"remain":[48],"limited":[49],"effectiveness":[51],"and":[52,68],"have":[53],"not":[54],"fully":[55],"eliminated":[56],"reliance":[57],"on":[58],"tuning.In":[60],"this":[61],"work,":[62],"we":[63],"propose":[64],"RMiPO,":[65],"lightweight":[67],"efficient":[69],"framework":[70],"for":[71,80],"offline":[72],"optimization.RMiPO":[74],"leverages":[75],"intrinsic":[76],"Response-level":[77],"Mutual":[78],"information":[79],"modulation,":[85],"dynamically":[86],"decoupling":[87],"contributions":[89],"at":[90,118],"negligible":[91],"computational":[93],"cost.Extensive":[94],"experimental":[95],"results":[96],"demonstrate":[97],"that":[98],"RMiPO":[99],"achieves":[100],"consistently":[101],"superior":[102],"over":[104],"existing":[105],"while":[107],"reducing":[108],"training":[109],"overhead":[110],"by":[111],"more":[112],"than":[113],"15%.Our":[114],"code":[115],"is":[116],"available":[117],"https://github.com/liavonpenn/rmipo.":[119]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}