{"id":"https://openalex.org/W7165782332","doi":"https://doi.org/10.48550/arxiv.2606.23915","title":"Do LLM Attribution Metrics Transfer? Auditing Retrieval-Augmented Generation Evaluation Across Datasets and Constructs","display_name":"Do LLM Attribution Metrics Transfer? Auditing Retrieval-Augmented Generation Evaluation Across Datasets and Constructs","publication_year":2026,"publication_date":"2026-06-22","ids":{"openalex":"https://openalex.org/W7165782332","doi":"https://doi.org/10.48550/arxiv.2606.23915"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.23915","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.23915","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.23915","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103030122","display_name":"Tianyu Ding","orcid":"https://orcid.org/0000-0001-8445-4330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Tianyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139282725","display_name":"Aditya Nannapaneni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nannapaneni, Aditya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138548247","display_name":"Juan Pablo De la Cruz Weinstein","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weinstein, Juan Pablo De la Cruz","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":0.17470000684261322,"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":0.17470000684261322,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.12860000133514404,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.09120000153779984,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6995000243186951},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.6643000245094299},{"id":"https://openalex.org/keywords/audit","display_name":"Audit","score":0.6133000254631042},{"id":"https://openalex.org/keywords/attribution","display_name":"Attribution","score":0.4668999910354614},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.45840001106262207},{"id":"https://openalex.org/keywords/interval","display_name":"Interval (graph theory)","score":0.4390000104904175},{"id":"https://openalex.org/keywords/truncation","display_name":"Truncation (statistics)","score":0.3928000032901764},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.3686000108718872}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7296000123023987},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6995000243186951},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.6643000245094299},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.6133000254631042},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.4668999910354614},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.45840001106262207},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.4390000104904175},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4050999879837036},{"id":"https://openalex.org/C106195933","wikidata":"https://www.wikidata.org/wiki/Q7847935","display_name":"Truncation (statistics)","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3806999921798706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37540000677108765},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C162838799","wikidata":"https://www.wikidata.org/wiki/Q596077","display_name":"Counterexample","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.23915","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.23915","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.23915","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.23915","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Practice":[0],"often":[1],"treats":[2],"automatic":[3,16,197],"metrics":[4],"for":[5,157],"attribution":[6,79],"in":[7],"LLM":[8,190],"retrieval-augmented":[9],"generation":[10],"as":[11],"interchangeable.":[12],"We":[13],"audit":[14],"eight":[15],"scorers":[17,198],"--":[18,34,77,93,212],"lexical,":[19],"embedding,":[20],"and":[21,28,42,112,210],"BERTScore":[22,134],"baselines":[23],"alongside":[24],"entailment/grounding-trained":[25],"models":[26],"(clean":[27],"FEVER":[29],"NLI,":[30],"the":[31,52,57,69,72,96,137,180,193,196,216],"checker":[32],"MiniCheck)":[33],"across":[35],"three":[36],"evaluation":[37],"constructs":[38],"(provenance/topicality,":[39],"generated-answer":[40,78],"attribution,":[41],"fact-check":[43],"entailment),":[44],"asking":[45],"whether":[46],"any":[47],"scorer":[48,60,116],"transfers:":[49],"stays":[50],"within":[51],"95%":[53],"confidence":[54],"interval":[55],"of":[56,64],"best":[58,119],"audited":[59],"on":[61,108,120,130,179],"every":[62],"dataset":[63,182],"a":[65,141,149,153],"multi-dataset":[66,74],"construct.":[67],"In":[68],"construct":[70],"with":[71,87],"most":[73],"human-labeled":[75],"coverage":[76],"(AttributionBench's":[80],"four":[81],"source":[82],"datasets,":[83],"n":[84,90],"=":[85,91,103,106],"1,610,":[86],"independent":[88],"HAGRID,":[89],"2,150)":[92],"none":[94],"does:":[95],"per-dataset":[97],"metric":[98,174],"rankings":[99],"invert":[100],"(Kendall":[101],"tau":[102],"-0.64,":[104],"p":[105],"0.031":[107],"AttributedQA":[109,122],"vs.":[110],"LFQA),":[111],"an":[113,159],"off-the-shelf":[114],"NLI":[115],"that":[117],"is":[118,139,204],"short-claim":[121],"(AUROC":[123],"0.90)":[124],"collapses":[125,195],"to":[126],"AUROC":[127],"0.53":[128],"(chance)":[129],"long-form":[131],"LFQA,":[132],"where":[133],"wins":[135],"(0.91);":[136],"flip":[138],"not":[140,205,214],"length":[142],"or":[143],"truncation":[144],"artifact.":[145],"This":[146],"instability":[147],"has":[148],"concrete":[150],"decision":[151],"cost:":[152],"naive":[154],"\"best-on-average\"":[155],"rule":[156],"choosing":[158],"evaluator":[160],"fails":[161],"leave-one-dataset-out":[162],"(mean":[163],"held-out":[164],"regret":[165],"0.172":[166],"AUROC,":[167],"worse":[168],"than":[169,184],"fixing":[170],"one":[171],"scorer),":[172],"so":[173],"choice":[175],"must":[176],"be":[177],"validated":[178],"target":[181],"rather":[183],"learned":[185],"from":[186],"others.":[187],"A":[188],"prompt-based":[189],"judge":[191],"avoids":[192],"chance-level":[194],"suffer":[199],"(no":[200],"LFQA":[201],"collapse)":[202],"but":[203],"uniformly":[206],"best,":[207],"~100x":[208],"costlier,":[209],"non-deterministic":[211],"relocating,":[213],"removing,":[215],"validation":[217],"burden.":[218]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-25T00:00:00"}