{"id":"https://openalex.org/W4416034661","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.594","title":"ReliableEval: A Recipe for Stochastic LLM Evaluation via Method of Moments","display_name":"ReliableEval: A Recipe for Stochastic LLM Evaluation via Method of Moments","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034661","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.594"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.594","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.594","pdf_url":"https://aclanthology.org/2025.findings-emnlp.594.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.594.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092031150","display_name":"Gili Lior","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gili Lior","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091921041","display_name":"Eliya Habba","orcid":"https://orcid.org/0009-0001-3472-0650"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eliya Habba","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112702972","display_name":"Shahar Levy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shahar Levy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077903013","display_name":"Avi Caciularu","orcid":"https://orcid.org/0000-0003-0573-1075"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Avi Caciularu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082136238","display_name":"Gabriel Stanovsky","orcid":"https://orcid.org/0000-0002-2420-8979"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gabriel Stanovsky","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":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11146","last_page":"11153"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.05460000038146973,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.05460000038146973,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.050999999046325684,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.03999999910593033,"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/recipe","display_name":"Recipe","score":0.49410000443458557},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.41499999165534973},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.28760001063346863},{"id":"https://openalex.org/keywords/calculus","display_name":"Calculus (dental)","score":0.2847000062465668},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.2639000117778778}],"concepts":[{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.49410000443458557},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44209998846054077},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4406000077724457},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.41499999165534973},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3815000057220459},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.35760000348091125},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33000001311302185},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28760001063346863},{"id":"https://openalex.org/C2777686260","wikidata":"https://www.wikidata.org/wiki/Q144037","display_name":"Calculus (dental)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.594","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.594","pdf_url":"https://aclanthology.org/2025.findings-emnlp.594.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.22169","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.22169","pdf_url":"https://arxiv.org/pdf/2505.22169","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:arXiv.org:2505.22169","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.22169","pdf_url":"https://arxiv.org/pdf/2505.22169","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.594","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.594","pdf_url":"https://aclanthology.org/2025.findings-emnlp.594.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034661.pdf","grobid_xml":"https://content.openalex.org/works/W4416034661.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"LLMs":[0,79],"are":[1],"highly":[2],"sensitive":[3],"to":[4,68],"prompt":[5,41,53,65,91],"phrasing,":[6],"yet":[7],"standard":[8],"benchmarks":[9],"typically":[10],"report":[11],"performance":[12],"using":[13],"a":[14,30,44,100],"single":[15],"prompt,":[16],"raising":[17],"concerns":[18],"about":[19],"the":[20,37,62],"reliability":[21],"of":[22,33,39,47,64],"such":[23],"evaluations.In":[24],"this":[25],"work,":[26],"we":[27,74],"argue":[28],"for":[29,52,60,102],"stochastic":[31],"method":[32,59],"moments":[34],"evaluation":[35,49],"over":[36],"space":[38],"meaningpreserving":[40],"perturbations.We":[42],"introduce":[43],"formal":[45],"definition":[46],"reliable":[48],"that":[50,82],"accounts":[51],"sensitivity,":[54],"and":[55,80,88,97,104],"suggest":[56],"RELIABLEEVAL":[57],"-a":[58],"estimating":[61],"number":[63],"resamplings":[66],"needed":[67],"obtain":[69],"meaningful":[70,103],"results.Using":[71],"our":[72],"framework,":[73],"stochastically":[75],"evaluate":[76],"five":[77],"frontier":[78],"find":[81],"even":[83],"top-performing":[84],"models":[85],"like":[86],"GPT-4o":[87],"Claude-3.7-Sonnetexhibit":[89],"substantial":[90],"sensitivity.Our":[92],"approach":[93],"is":[94],"model-,":[95],"task-,":[96],"metric-agnostic,":[98],"offering":[99],"recipe":[101],"robust":[105],"LLM":[106],"evaluation.":[107],"1":[108]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}