{"id":"https://openalex.org/W7166827766","doi":"https://doi.org/10.18653/v1/2026.acl-long.927","title":"PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling","display_name":"PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166827766","doi":"https://doi.org/10.18653/v1/2026.acl-long.927"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.927","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.927","pdf_url":"https://aclanthology.org/2026.acl-long.927.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.927.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139736528","display_name":"Ai Jian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152823","display_name":"China Meat Research Centre","ror":"https://ror.org/05jc4yc89","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210152823"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ai Jian","raw_affiliation_strings":["Meituan , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan , Beijing , China","institution_ids":["https://openalex.org/I4210152823"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076546255","display_name":"Jingqing Ruan","orcid":"https://orcid.org/0000-0002-4857-9053"},"institutions":[{"id":"https://openalex.org/I4210152823","display_name":"China Meat Research Centre","ror":"https://ror.org/05jc4yc89","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210152823"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingqing Ruan","raw_affiliation_strings":["Meituan , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan , Beijing , China","institution_ids":["https://openalex.org/I4210152823"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139843542","display_name":"Xing Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152823","display_name":"China Meat Research Centre","ror":"https://ror.org/05jc4yc89","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210152823"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Ma","raw_affiliation_strings":["Meituan , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan , Beijing , China","institution_ids":["https://openalex.org/I4210152823"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000533603","display_name":"Dailin Li","orcid":"https://orcid.org/0009-0003-5731-1790"},"institutions":[{"id":"https://openalex.org/I4210152823","display_name":"China Meat Research Centre","ror":"https://ror.org/05jc4yc89","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210152823"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dailin Li","raw_affiliation_strings":["Meituan , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan , Beijing , China","institution_ids":["https://openalex.org/I4210152823"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139839206","display_name":"Weipeng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152823","display_name":"China Meat Research Centre","ror":"https://ror.org/05jc4yc89","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210152823"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weipeng Zhang","raw_affiliation_strings":["Meituan , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan , Beijing , China","institution_ids":["https://openalex.org/I4210152823"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139839379","display_name":"Ke Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152823","display_name":"China Meat Research Centre","ror":"https://ror.org/05jc4yc89","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210152823"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Zeng","raw_affiliation_strings":["Meituan , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan , Beijing , China","institution_ids":["https://openalex.org/I4210152823"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139817245","display_name":"Xunliang Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152823","display_name":"China Meat Research Centre","ror":"https://ror.org/05jc4yc89","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210152823"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xunliang Cai","raw_affiliation_strings":["Meituan , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan , Beijing , China","institution_ids":["https://openalex.org/I4210152823"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210152823"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84726504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20240","last_page":"20268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.5728999972343445,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.5728999972343445,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10667","display_name":"Emotion and Mood Recognition","score":0.08560000360012054,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.024900000542402267,"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/pointwise","display_name":"Pointwise","score":0.8104000091552734},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.6098999977111816},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4846000075340271},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.30550000071525574}],"concepts":[{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.8104000091552734},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6098999977111816},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4846000075340271},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4821000099182129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4278999865055084},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3310999870300293},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.2874999940395355},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2460000067949295}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.927","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.927","pdf_url":"https://aclanthology.org/2026.acl-long.927.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.927","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.927","pdf_url":"https://aclanthology.org/2026.acl-long.927.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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166827766.pdf","grobid_xml":"https://content.openalex.org/works/W7166827766.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reward":[0,66,85],"models":[1,21,27,124],"(RMs)":[2],"are":[3,45,171],"central":[4],"to":[5],"reinforcement":[6],"learning":[7],"from":[8],"human":[9,24],"feedback":[10],"(RLHF),":[11],"providing":[12],"the":[13,63,89,121,130,153],"critical":[14,41],"supervision":[15],"signals":[16],"that":[17,101,111],"align":[18],"large":[19],"language":[20],"(LLMs)":[22],"with":[23,39],"preferences.Generative":[25],"reward":[26,139],"(GRMs)":[28],"provide":[29],"greater":[30],"interpretability":[31],"than":[32],"traditional":[33],"scalar":[34],"RMs,":[35],"but":[36],"they":[37],"come":[38],"a":[40,48,82,97,138],"trade-off:":[42],"pairwise":[43,79],"methods":[44,53],"hindered":[46],"by":[47],"training-inference":[49],"mismatch,":[50],"while":[51],"pointwise":[52,74],"require":[54],"expensive":[55],"absolute":[56],"annotations.To":[57],"bridge":[58],"this":[59],"gap,":[60],"we":[61],"propose":[62],"Preference-aware":[64],"Task-adaptive":[65],"Model":[67],"(PaTaRM).Unlike":[68],"prior":[69],"approaches,":[70],"PaTaRM":[71,112],"enables":[72],"robust":[73],"training":[75],"using":[76],"readily":[77],"available":[78,172],"data":[80],"via":[81],"novel":[83],"Preference-Aware":[84],"(PAR)":[86],"mechanism,":[87],"eliminating":[88],"need":[90],"for":[91,106,141,164],"explicit":[92],"rating":[93],"labels.Furthermore,":[94],"it":[95,144],"incorporates":[96],"taskadaptive":[98],"rubric":[99],"system":[100],"dynamically":[102],"generates":[103],"instance-specific":[104],"criteria":[105],"precise":[107],"evaluation.Extensive":[108],"experiments":[109],"demonstrate":[110],"achieves":[113],"an":[114,146],"average":[115,147],"relative":[116,148],"improvement":[117,149],"of":[118,150],"8.7%":[119],"over":[120,152],"corresponding":[122,154],"base":[123,155],"on":[125,157],"RewardBench":[126],"and":[127,132,159,169],"RMBench":[128],"across":[129],"Qwen3-8B":[131],"Qwen3-14B":[133],"backbones.Crucially,":[134],"when":[135],"used":[136],"as":[137],"model":[140],"downstream":[142],"RLHF,":[143],"yields":[145],"13.6%":[151],"policies":[156],"IFEval":[158],"InfoBench,":[160],"validating":[161],"its":[162],"effectiveness":[163],"policy":[165],"alignment.Our":[166],"code,":[167],"data,":[168],"checkpoints":[170],"at":[173],"https://huggingface.co/AIJian/PaTaRM.":[174]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}