{"id":"https://openalex.org/W7166873827","doi":"https://doi.org/10.18653/v1/2026.acl-long.567","title":"Reward Modeling for Scientific Writing Evaluation","display_name":"Reward Modeling for Scientific Writing Evaluation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166873827","doi":"https://doi.org/10.18653/v1/2026.acl-long.567"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.567","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.567","pdf_url":"https://aclanthology.org/2026.acl-long.567.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.567.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003367589","display_name":"Furkan \u015eahi\u0307nu\u00e7","orcid":"https://orcid.org/0000-0001-9104-2860"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Furkan \u015eahinu\u00e7","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139727520","display_name":"Subhabrata Dutta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Subhabrata Dutta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139767996","display_name":"Iryna Gurevych","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iryna Gurevych","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":0.96953367,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12438","last_page":"12479"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12070","display_name":"Writing and Handwriting Education","score":0.10610000044107437,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12070","display_name":"Writing and Handwriting Education","score":0.10610000044107437,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.06539999693632126,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.05530000105500221,"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/rubric","display_name":"Rubric","score":0.6241999864578247},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5885999798774719},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5365999937057495},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4334000051021576},{"id":"https://openalex.org/keywords/scientific-writing","display_name":"Scientific writing","score":0.4327999949455261},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4325000047683716},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.37439998984336853},{"id":"https://openalex.org/keywords/scientific-modelling","display_name":"Scientific modelling","score":0.35190001130104065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7749999761581421},{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.6241999864578247},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5885999798774719},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5365999937057495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4447999894618988},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4334000051021576},{"id":"https://openalex.org/C2778949450","wikidata":"https://www.wikidata.org/wiki/Q1965486","display_name":"Scientific writing","level":2,"score":0.4327999949455261},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4325000047683716},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36500000953674316},{"id":"https://openalex.org/C138379479","wikidata":"https://www.wikidata.org/wiki/Q1116876","display_name":"Scientific modelling","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C100521375","wikidata":"https://www.wikidata.org/wiki/Q2015382","display_name":"Competence (human resources)","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C2992562121","wikidata":"https://www.wikidata.org/wiki/Q3817808","display_name":"Scientific reasoning","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34279999136924744},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3001999855041504},{"id":"https://openalex.org/C195732255","wikidata":"https://www.wikidata.org/wiki/Q981008","display_name":"Sociology of scientific knowledge","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C92548554","wikidata":"https://www.wikidata.org/wiki/Q2262868","display_name":"Domain model","level":3,"score":0.2603999972343445},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.2572999894618988},{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.567","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.567","pdf_url":"https://aclanthology.org/2026.acl-long.567.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.567","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.567","pdf_url":"https://aclanthology.org/2026.acl-long.567.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":[{"score":0.7687122225761414,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320875","display_name":"Deutscher Akademischer Austauschdienst","ror":"https://ror.org/039djdh30"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320323384","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166873827.pdf","grobid_xml":"https://content.openalex.org/works/W7166873827.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Scientific":[0],"writing":[1,56,124,172,184],"is":[2,41,105],"an":[3],"expert-domain":[4],"task":[5,24,104],"that":[6,16,46,131,164],"demands":[7],"deep":[8],"domain":[9,19],"knowledge,":[10],"task-specific":[11,196],"requirements":[12],"and":[13,38,67,80,97,107,137,145,154,159,179,202],"reasoning":[14,140],"capabilities":[15],"leverage":[17],"the":[18,23],"knowledge":[20,90],"to":[21,43,60,86,156,180,192],"satisfy":[22],"specifications.While":[25],"scientific":[26,55,92,123,134,171,183],"text":[27],"generation":[28],"has":[29],"been":[30],"widely":[31],"studied,":[32],"its":[33],"evaluation":[34,81,135,143,185],"remains":[35],"a":[36,127,188],"challenging":[37],"open":[39],"problem.It":[40],"critical":[42],"develop":[44],"models":[45,69,120,174],"can":[47],"be":[48,193],"reliably":[49],"deployed":[50],"for":[51,73,101,109,122],"evaluating":[52],"diverse":[53,149],"openended":[54],"tasks":[57,150,178],"while":[58],"adhering":[59],"their":[61],"distinct":[62],"requirements.However,":[63],"existing":[64],"LLM-based":[65,170],"judges":[66],"reward":[68,119],"are":[70],"primarily":[71],"optimized":[72],"general-purpose":[74],"benchmarks":[75],"with":[76],"fixed":[77],"scoring":[78,160],"rubrics":[79],"criteria.Consequently,":[82],"they":[83],"often":[84],"fail":[85],"reason":[87],"over":[88],"sparse":[89],"of":[91],"domains":[93],"when":[94],"interpreting":[95],"task-dependent":[96],"multi-faceted":[98],"criteria.Moreover,":[99],"fine-tuning":[100],"each":[102],"individual":[103],"costly":[106],"impractical":[108],"low-resource":[110],"settings.To":[111],"bridge":[112],"these":[113],"gaps,":[114],"we":[115],"propose":[116],"cost-efficient,":[117],"open-source":[118],"tailored":[121],"evaluation.We":[125],"introduce":[126],"two-stage":[128],"training":[129,147,166],"framework":[130],"initially":[132],"optimizes":[133],"preferences":[136],"then":[138],"refines":[139],"capabilities.Our":[141],"multi-aspect":[142],"design":[144],"joint":[146],"across":[148,177],"enable":[151],"fine-grained":[152],"assessment":[153],"robustness":[155],"dynamic":[157],"criteria":[158],"rubrics.Experimental":[161],"analysis":[162],"shows":[163],"our":[165,199],"regime":[167],"strongly":[168],"improves":[169],"evaluation.Our":[173],"generalize":[175],"effectively":[176],"previously":[181],"unseen":[182],"settings,":[186],"allowing":[187],"single":[189],"trained":[190],"evaluator":[191],"reused":[194],"without":[195],"retraining.We":[197],"make":[198],"code":[200],"1":[201],"data":[203],"2":[204],"publicly":[205],"available.":[206]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}