{"id":"https://openalex.org/W7162514913","doi":"https://doi.org/10.48550/arxiv.2605.27204","title":"GraphReview: Scientific Paper Evaluation via LLM-based Graph Evidence Expansion","display_name":"GraphReview: Scientific Paper Evaluation via LLM-based Graph Evidence Expansion","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W7162514913","doi":"https://doi.org/10.48550/arxiv.2605.27204"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.27204","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27204","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2605.27204","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137150471","display_name":"Pujun Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Pujun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137114292","display_name":"Wanying Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Wanying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137147404","display_name":"Jiacheng Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Jiacheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000341481","display_name":"Guoxiu He","orcid":"https://orcid.org/0000-0002-1419-7495"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Guoxiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5030902016","display_name":"Star X. Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Star X.","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/T11273","display_name":"Advanced Graph Neural Networks","score":0.5443000197410583,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.5443000197410583,"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":0.10859999805688858,"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/T10028","display_name":"Topic Modeling","score":0.05490000173449516,"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/pairwise-comparison","display_name":"Pairwise comparison","score":0.6956999897956848},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6021999716758728},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.564300000667572},{"id":"https://openalex.org/keywords/pagerank","display_name":"PageRank","score":0.5164999961853027},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5080999732017517},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.46639999747276306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7472000122070312},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6956999897956848},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6021999716758728},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.564300000667572},{"id":"https://openalex.org/C2779172887","wikidata":"https://www.wikidata.org/wiki/Q184316","display_name":"PageRank","level":2,"score":0.5164999961853027},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5080999732017517},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.46639999747276306},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4032999873161316},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3977999985218048},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3416000008583069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3361000120639801},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3165999948978424},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3138999938964844},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.27204","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27204","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":"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":"doi:10.48550/arxiv.2605.27204","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27204","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.5205938220024109,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Scientific":[0],"paper":[1,50,60,94],"evaluation":[2,51],"often":[3],"involves":[4],"not":[5],"only":[6],"assessing":[7],"a":[8,32,44,58],"manuscript":[9],"itself,":[10],"but":[11],"also":[12,158],"relating":[13],"it":[14],"to":[15,76,82],"contemporaneous":[16,71],"research":[17],"and":[18,30,73,87,108,143,152,163,169],"prior":[19,77],"literature.":[20],"However,":[21],"existing":[22],"LLM-based":[23],"methods":[24],"typically":[25],"model":[26],"these":[27,100],"signals":[28,102],"separately":[29],"lack":[31],"unified":[33],"mechanism":[34],"for":[35,103,122],"aggregating":[36],"review":[37,109,161],"evidence":[38,55,91],"across":[39,166],"papers.":[40],"We":[41],"propose":[42,117],"$\\textbf{GraphReview}$,":[43],"graph-based":[45],"LLM":[46,125],"framework":[47],"that":[48,129],"formulates":[49],"as":[52],"inference-time":[53],"graph":[54,63,114],"expansion":[56],"over":[57],"semantic":[59],"graph.":[61],"The":[62],"jointly":[64],"captures":[65],"intrinsic":[66],"quality,":[67],"synchronic":[68],"links":[69,75],"among":[70],"papers,":[72],"diachronic":[74],"work.":[78],"LLMs":[79],"are":[80],"used":[81],"estimate":[83],"node-level":[84],"quality":[85,104],"priors":[86],"generate":[88],"edge-level":[89],"comparative":[90],"through":[92],"pairwise":[93],"comparisons,":[95],"while":[96],"Personalized":[97],"PageRank":[98],"integrates":[99],"structured":[101],"ranking,":[105],"decision":[106,142],"prediction,":[107],"generation.":[110],"To":[111],"produce":[112],"higher-quality":[113,160],"evidence,":[115],"we":[116],"reward-induced":[118],"maximum":[119],"likelihood":[120],"objectives":[121],"training":[123],"the":[124,133],"backbones.":[126],"Experiments":[127],"show":[128],"GraphReview":[130],"consistently":[131],"outperforms":[132],"strongest":[134],"baseline,":[135],"achieving":[136],"average":[137],"improvements":[138],"of":[139,148],"29.7%":[140],"on":[141],"ranking":[144],"metrics,":[145],"including":[146],"gains":[147],"23.7%":[149],"in":[150,154],"Accuracy":[151],"57.6%":[153],"Spearman's":[155],"$\u03c1$.":[156],"It":[157],"produces":[159],"texts":[162],"generalizes":[164],"effectively":[165],"time":[167],"periods":[168],"conference":[170],"venues.":[171]},"counts_by_year":[],"updated_date":"2026-08-12T07:12:00.856984","created_date":"2026-05-28T00:00:00"}