{"id":"https://openalex.org/W4416243136","doi":"https://doi.org/10.48550/arxiv.2508.07955","title":"Expert Preference-based Evaluation of Automated Related Work Generation","display_name":"Expert Preference-based Evaluation of Automated Related Work Generation","publication_year":2025,"publication_date":"2025-08-11","ids":{"openalex":"https://openalex.org/W4416243136","doi":"https://doi.org/10.48550/arxiv.2508.07955"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2508.07955","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2508.07955","pdf_url":"https://arxiv.org/pdf/2508.07955","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.07955","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003367589","display_name":"Furkan \u015eahi\u0307nu\u00e7","orcid":"https://orcid.org/0000-0001-9104-2860","observed_orcids":["https://orcid.org/0000-0001-9104-2860"]},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I4392021234","display_name":"Hessian Center for Artificial Intelligence","ror":"https://ror.org/014ybqb54","country_code":"DE","type":"facility","lineage":["https://openalex.org/I31512782","https://openalex.org/I4392021234"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"\u015eahinu\u00e7, Furkan","raw_affiliation_strings":["Konrad Zuse School of Excellence in Learning and Intelligent Systems (ELIZA)","Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science and Hessian Center for AI (hessian.AI) Technical University of Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Konrad Zuse School of Excellence in Learning and Intelligent Systems (ELIZA)","institution_ids":[]},{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science and Hessian Center for AI (hessian.AI) Technical University of Darmstadt","institution_ids":["https://openalex.org/I31512782","https://openalex.org/I4392021234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023507685","display_name":"Subhabrata Dutta","orcid":"https://orcid.org/0000-0002-0730-0685","observed_orcids":["https://orcid.org/0000-0002-0730-0685"]},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I4392021234","display_name":"Hessian Center for Artificial Intelligence","ror":"https://ror.org/014ybqb54","country_code":"DE","type":"facility","lineage":["https://openalex.org/I31512782","https://openalex.org/I4392021234"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dutta, Subhabrata","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science and Hessian Center for AI (hessian.AI) Technical University of Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science and Hessian Center for AI (hessian.AI) Technical University of Darmstadt","institution_ids":["https://openalex.org/I31512782","https://openalex.org/I4392021234"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027450194","display_name":"Iryna Gurevych","orcid":"https://orcid.org/0000-0003-2187-7621","observed_orcids":["https://orcid.org/0000-0003-2187-7621"]},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I4392021234","display_name":"Hessian Center for Artificial Intelligence","ror":"https://ror.org/014ybqb54","country_code":"DE","type":"facility","lineage":["https://openalex.org/I31512782","https://openalex.org/I4392021234"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gurevych, Iryna","raw_affiliation_strings":["Konrad Zuse School of Excellence in Learning and Intelligent Systems (ELIZA)","Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science and Hessian Center for AI (hessian.AI) Technical University of Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Konrad Zuse School of Excellence in Learning and Intelligent Systems (ELIZA)","institution_ids":[]},{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science and Hessian Center for AI (hessian.AI) Technical University of Darmstadt","institution_ids":["https://openalex.org/I31512782","https://openalex.org/I4392021234"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.548799991607666,"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":0.548799991607666,"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":0.10599999874830246,"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/T12648","display_name":"Academic Writing and Publishing","score":0.08969999849796295,"subfield":{"id":"https://openalex.org/subfields/1207","display_name":"History and Philosophy of Science"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scientific-writing","display_name":"scientific writing","score":0.8349999785423279},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7419999837875366},{"id":"https://openalex.org/keywords/expert-preferences","display_name":"expert preferences","score":0.4620000123977661},{"id":"https://openalex.org/keywords/evaluation-criteria","display_name":"evaluation criteria","score":0.5910000205039978},{"id":"https://openalex.org/keywords/llm-as-a-judge","display_name":"LLM-as-a-judge","score":0.8149999976158142},{"id":"https://openalex.org/keywords/fine-grained-evaluation","display_name":"fine-grained evaluation","score":0.7400000095367432}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7282999753952026},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.6118000149726868},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6025000214576721},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5677000284194946},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4781000018119812},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.4672999978065491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.426800012588501},{"id":"https://openalex.org/C2777617010","wikidata":"https://www.wikidata.org/wiki/Q18957","display_name":"Mainstream","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3418000042438507},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2973000109195709},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2736000120639801},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2687000036239624},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2623000144958496}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2508.07955","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2508.07955","pdf_url":"https://arxiv.org/pdf/2508.07955","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.07955","doi":"https://doi.org/10.48550/arxiv.2508.07955","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.07955","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.07955","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2508.07955","pdf_url":"https://arxiv.org/pdf/2508.07955","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[{"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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416243136.pdf","grobid_xml":"https://content.openalex.org/works/W4416243136.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Expert":[0],"domain":[1,10],"writing,":[2,6,82,173],"such":[3],"as":[4,36,96],"scientific":[5,29,94,172],"typically":[7],"demands":[8],"extensive":[9],"knowledge.":[11],"Although":[12],"large":[13],"language":[14],"models":[15],"(LLMs)":[16],"show":[17],"promising":[18],"potential":[19],"in":[20,157],"this":[21,75],"task,":[22],"evaluating":[23],"the":[24,44,91,118,139,151,180],"quality":[25,71,152],"of":[26,40,90,153,171,182,198],"automatically":[27],"generated":[28],"writing":[30],"is":[31,127,147],"a":[32,102,158,176,199],"crucial":[33],"open":[34],"issue,":[35],"it":[37],"requires":[38],"knowledge":[39],"domain-specific":[41,70],"criteria":[42,112],"and":[43,54,69,77,174],"ability":[45],"to":[46,65,133,149,164,194],"discern":[47],"expert":[48,67],"preferences.":[49,115],"Conventional":[50],"automatic":[51],"evaluation":[52,104,111,119,126,140],"metrics":[53],"LLM-as-a-judge":[55],"systems,":[56],"primarily":[57],"designed":[58],"for":[59,138],"mainstream":[60],"NLP":[61],"tasks,":[62,95],"are":[63],"insufficient":[64],"grasp":[66],"preferences":[68],"standards.":[72],"To":[73],"address":[74],"gap":[76],"support":[78],"realistic":[79],"human-AI":[80],"collaborative":[81],"we":[83],"focus":[84],"on":[85],"related":[86,109,154,201],"work":[87,110,155,202],"generation,":[88],"one":[89],"most":[92],"challenging":[93],"an":[97],"exemplar.":[98],"We":[99,185],"propose":[100],"GREP,":[101],"multi-turn":[103],"framework":[105],"that":[106,145,188],"integrates":[107],"classical":[108],"with":[113,130,179],"expert-specific":[114],"GREP":[116,146],"decomposes":[117],"into":[120],"smaller":[121],"fine-grained":[122],"dimensions.":[123,141],"This":[124],"localized":[125],"further":[128],"augmented":[129],"contrastive":[131],"examples":[132],"provide":[134],"detailed":[135],"contextual":[136],"guidance":[137],"Empirical":[142],"investigation":[143],"reveals":[144],"able":[148],"assess":[150],"sections":[156],"much":[159],"more":[160],"robust":[161],"manner":[162],"compared":[163],"standard":[165],"LLM":[166],"judges,":[167],"reflects":[168],"natural":[169],"scenarios":[170],"bears":[175],"strong":[177],"correlation":[178],"assessment":[181],"human":[183],"experts.":[184],"also":[186],"observe":[187],"generations":[189],"from":[190],"state-of-the-art":[191],"LLMs":[192],"struggle":[193],"satisfy":[195],"validation":[196],"constraints":[197],"suitable":[200],"section.":[203]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2025-10-10T00:00:00"}