{"id":"https://openalex.org/W7166809376","doi":"https://doi.org/10.18653/v1/2026.acl-long.1789","title":"Teaching LLMs Human-Like Editing of Inappropriate Argumentation via Reinforcement Learning","display_name":"Teaching LLMs Human-Like Editing of Inappropriate Argumentation via Reinforcement Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166809376","doi":"https://doi.org/10.18653/v1/2026.acl-long.1789"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1789","doi":"https://doi.org/10.18653/v1/2026.acl-long.1789","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1789","pdf_url":"https://aclanthology.org/2026.acl-long.1789.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.acl-long.1789.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092029610","display_name":"Timon Ziegenbein","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Timon Ziegenbein","raw_affiliation_strings":["Leibniz University Hannover"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz University Hannover","institution_ids":["https://openalex.org/I114112103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101671192","display_name":"Maja Stahl","orcid":"https://orcid.org/0000-0002-5982-726X","observed_orcids":["https://orcid.org/0000-0002-5982-726X"]},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maja Stahl","raw_affiliation_strings":["Leibniz University Hannover"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz University Hannover","institution_ids":["https://openalex.org/I114112103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014375244","display_name":"Henning Wachsmuth","orcid":"https://orcid.org/0000-0003-2792-621X","observed_orcids":["https://orcid.org/0000-0003-2792-621X"]},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]},{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Henning Wachsmuth","raw_affiliation_strings":["Leibniz University Hannover , L3S Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz University Hannover , L3S Research Center","institution_ids":["https://openalex.org/I114112103","https://openalex.org/I4210136150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.6106,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97163131,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"38616","last_page":"38637"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5615000128746033,"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":0.5615000128746033,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.3190999925136566,"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/T12031","display_name":"Speech and dialogue systems","score":0.024299999698996544,"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/large-language-models","display_name":"large language models","score":0.6460000276565552},{"id":"https://openalex.org/keywords/text-editing","display_name":"text editing","score":0.7710000276565552},{"id":"https://openalex.org/keywords/argumentation","display_name":"argumentation","score":0.6869999766349792},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.6420000195503235},{"id":"https://openalex.org/keywords/group-relative-policy-optimization","display_name":"Group Relative Policy Optimization","score":0.8600000143051147},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"semantic similarity","score":0.6840000152587891},{"id":"https://openalex.org/keywords/fluency","display_name":"fluency","score":0.8820000290870667},{"id":"https://openalex.org/keywords/meaning-preservation","display_name":"meaning preservation","score":0.5350000262260437}],"concepts":[{"id":"https://openalex.org/C65059942","wikidata":"https://www.wikidata.org/wiki/Q270105","display_name":"Argumentation theory","level":2,"score":0.5315999984741211},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.44859999418258667},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.3756999969482422},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.34290000796318054},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.30790001153945923},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.3061000108718872},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3028999865055084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30149999260902405},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2703999876976013},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.2703000009059906},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2574999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1789","doi":"https://doi.org/10.18653/v1/2026.acl-long.1789","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1789","pdf_url":"https://aclanthology.org/2026.acl-long.1789.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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.1789","doi":"https://doi.org/10.18653/v1/2026.acl-long.1789","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1789","pdf_url":"https://aclanthology.org/2026.acl-long.1789.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166809376.pdf","grobid_xml":"https://content.openalex.org/works/W7166809376.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4399448085","https://openalex.org/W4389520370","https://openalex.org/W4416034156","https://openalex.org/W4417449794","https://openalex.org/W7125919604","https://openalex.org/W4402669970","https://openalex.org/W4416035869","https://openalex.org/W4416034628","https://openalex.org/W7125514667","https://openalex.org/W4389518949"],"abstract_inverted_index":{"Editing":[0],"human-written":[1],"text":[2],"has":[3],"become":[4],"a":[5,23,32,63,100],"standard":[6],"use":[7],"case":[8],"of":[9,76,130],"large":[10],"language":[11],"models":[12],"(LLMs),":[13],"for":[14,22],"example,":[15],"to":[16,26,46,72,142],"make":[17],"one's":[18],"arguments":[19],"more":[20],"appropriate":[21],"discussion.Comparing":[24],"human":[25,121],"LLM-generated":[27],"edits,":[28],"however,":[29],"we":[30,61],"observe":[31],"mismatch":[33],"in":[34,55,133],"editing":[35,71,138],"strategies:":[36],"While":[37],"LLMs":[38,69],"often":[39],"perform":[40],"multiple":[41],"scattered":[42],"edits":[43],"and":[44,111,120,127],"tend":[45],"change":[47],"meaning":[48],"notably,":[49],"humans":[50],"rather":[51],"encapsulate":[52],"dependent":[53],"changes":[54],"selfcontained,":[56],"meaning-preserving":[57],"edits.In":[58],"this":[59],"paper,":[60],"present":[62],"reinforcement":[64],"learning":[65],"approach":[66,78,93],"that":[67,84,104],"teaches":[68],"human-like":[70],"improve":[73],"the":[74,92,128,131],"appropriateness":[75,140],"arguments.Our":[77],"produces":[79],"self-contained":[80],"sentence-level":[81],"edit":[82],"suggestions":[83],"can":[85],"be":[86],"accepted":[87],"or":[88],"rejected":[89],"independently.We":[90],"train":[91],"using":[94],"group":[95],"relative":[96],"policy":[97],"optimization":[98],"with":[99,136],"multi-component":[101],"reward":[102],"function":[103],"jointly":[105],"optimizes":[106],"edit-level":[107],"semantic":[108],"similarity,":[109],"fluency,":[110],"pattern":[112],"conformity":[113],"as":[114,116],"well":[115],"argument-level":[117],"appropriateness.In":[118],"automatic":[119],"evaluation,":[122],"it":[123],"outperforms":[124],"competitive":[125],"baselines":[126],"state":[129],"art":[132],"humanlike":[134],"editing,":[135],"multi-round":[137],"achieving":[139],"close":[141],"full":[143],"rewriting.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-07-02T00:00:00"}