{"id":"https://openalex.org/W7134966993","doi":"https://doi.org/10.48550/arxiv.2603.09723","title":"RbtAct: Rebuttal as Supervision for Actionable Review Feedback Generation","display_name":"RbtAct: Rebuttal as Supervision for Actionable Review Feedback Generation","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7134966993","doi":"https://doi.org/10.48550/arxiv.2603.09723"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.09723","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.09723","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,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.09723","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074122965","display_name":"Sihong Wu","orcid":"https://orcid.org/0000-0003-3070-8715"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Sihong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128776534","display_name":"Yiling Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Yiling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128748995","display_name":"Yilun Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yilun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119963925","display_name":"Tiansheng Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Tiansheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114972132","display_name":"Owen Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Owen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027458097","display_name":"Manasi Patwardhan","orcid":"https://orcid.org/0000-0002-2775-3497"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patwardhan, Manasi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128722816","display_name":"Arman Cohan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cohan, Arman","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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.28200000524520874,"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":0.28200000524520874,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.19850000739097595,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.08799999952316284,"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/rebuttal","display_name":"Rebuttal","score":0.9962000250816345},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7175999879837036},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6165000200271606},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4453999996185303},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42910000681877136},{"id":"https://openalex.org/keywords/warrant","display_name":"Warrant","score":0.4180999994277954}],"concepts":[{"id":"https://openalex.org/C2777310092","wikidata":"https://www.wikidata.org/wiki/Q1410600","display_name":"Rebuttal","level":2,"score":0.9962000250816345},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7175999879837036},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6165000200271606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47510001063346863},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4453999996185303},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C2776916960","wikidata":"https://www.wikidata.org/wiki/Q637156","display_name":"Warrant","level":2,"score":0.4180999994277954},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.4083999991416931},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34779998660087585},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.30309998989105225},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30149999260902405},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2793000042438507},{"id":"https://openalex.org/C2780554381","wikidata":"https://www.wikidata.org/wiki/Q2063340","display_name":"Sensemaking","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27390000224113464},{"id":"https://openalex.org/C29554801","wikidata":"https://www.wikidata.org/wiki/Q147027","display_name":"Thought experiment","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.09723","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.09723","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,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.09723","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.09723","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,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6728910803794861}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4,20],"increasingly":[5],"used":[6],"across":[7],"the":[8,33,54,110,122,147,166],"scientific":[9],"workflow,":[10],"including":[11],"to":[12,64,85,114,146],"draft":[13],"peer-review":[14],"reports.":[15],"However,":[16],"many":[17],"AI-generated":[18],"reviews":[19],"superficial":[21],"and":[22,31,47,70,125,132,156,187,194,202],"insufficiently":[23],"actionable,":[24],"leaving":[25],"authors":[26],"without":[27],"concrete,":[28],"implementable":[29],"guidance":[30],"motivating":[32],"gap":[34],"this":[35,77,95],"work":[36],"addresses.":[37],"We":[38,134,163],"propose":[39,98],"RbtAct,":[40],"which":[41,60,71,109],"targets":[42],"actionable":[43],"review":[44,51,105,144,173],"feedback":[45,89,106],"generation":[46],"places":[48],"existing":[49],"peer":[50],"rebuttal":[52,81,148,180],"at":[53],"center":[55],"of":[56],"learning.":[57],"Rebuttals":[58],"show":[59,189],"reviewer":[61],"comments":[62],"led":[63],"concrete":[65],"revisions":[66],"or":[67],"specific":[68],"plans,":[69],"were":[72],"only":[73],"defended.":[74],"Building":[75],"on":[76,121,172],"insight,":[78],"we":[79,97],"leverage":[80],"as":[82,130],"implicit":[83],"supervision":[84],"directly":[86],"optimize":[87],"a":[88,99,116,126,137],"generator":[90],"for":[91],"actionability.":[92],"To":[93],"support":[94],"objective,":[96],"new":[100],"task":[101],"called":[102],"perspective-conditioned":[103],"segment-level":[104],"generation,":[107],"in":[108,192],"model":[111,168],"is":[112],"required":[113],"produce":[115],"single":[117],"focused":[118],"comment":[119],"based":[120],"complete":[123],"paper":[124],"specified":[127],"perspective":[128,154],"such":[129],"experiments":[131],"writing.":[133],"also":[135],"build":[136],"large":[138],"dataset":[139],"named":[140],"RMR-75K":[141],"that":[142,150,159],"maps":[143],"segments":[145,149,174],"address":[151],"them,":[152],"with":[153,169,184],"labels":[155],"impact":[157],"categories":[158],"order":[160],"author":[161],"uptake.":[162],"then":[164],"train":[165],"Llama-3.1-8B-Instruct":[167],"supervised":[170],"fine-tuning":[171],"followed":[175],"by":[176],"preference":[177],"optimization":[178],"using":[179],"derived":[181],"pairs.":[182],"Experiments":[183],"human":[185],"experts":[186],"LLM-as-a-judge":[188],"consistent":[190],"gains":[191],"actionability":[193],"specificity":[195],"over":[196],"strong":[197],"baselines":[198],"while":[199],"maintaining":[200],"grounding":[201],"relevance.":[203]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-12T00:00:00"}