{"id":"https://openalex.org/W4412888716","doi":"https://doi.org/10.18653/v1/2025.findings-acl.212","title":"ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty","display_name":"ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888716","doi":"https://doi.org/10.18653/v1/2025.findings-acl.212"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.212","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.212","pdf_url":"https://aclanthology.org/2025.findings-acl.212.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: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.212.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093047682","display_name":"Qing Zong","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["HK","PK"],"is_corresponding":false,"raw_author_name":"Qing Zong","raw_affiliation_strings":["Department of Computer Science and Engineering , HKUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , HKUST","institution_ids":["https://openalex.org/I929597975","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100655139","display_name":"Zhaowei Wang","orcid":"https://orcid.org/0009-0004-8565-8326"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["HK","PK"],"is_corresponding":false,"raw_author_name":"Zhaowei Wang","raw_affiliation_strings":["Department of Computer Science and Engineering , HKUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , HKUST","institution_ids":["https://openalex.org/I929597975","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031583104","display_name":"Tianshi Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["HK","PK"],"is_corresponding":false,"raw_author_name":"Tianshi Zheng","raw_affiliation_strings":["Department of Computer Science and Engineering , HKUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , HKUST","institution_ids":["https://openalex.org/I929597975","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiyu Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["HK","PK"],"is_corresponding":false,"raw_author_name":"Xiyu Ren","raw_affiliation_strings":["Department of Computer Science and Engineering , HKUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , HKUST","institution_ids":["https://openalex.org/I929597975","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020880385","display_name":"Yangqiu Song","orcid":"https://orcid.org/0000-0002-7818-6090"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["HK","PK"],"is_corresponding":false,"raw_author_name":"Yangqiu Song","raw_affiliation_strings":["Department of Computer Science and Engineering , HKUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , HKUST","institution_ids":["https://openalex.org/I929597975","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"4101","last_page":"4117"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.5819000005722046,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.5819000005722046,"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/T11891","display_name":"Big Data and Business Intelligence","score":0.5745999813079834,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.5734000205993652,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.8472191095352173},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5665696859359741},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.367426335811615},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06660827994346619}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8472191095352173},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5665696859359741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.367426335811615},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06660827994346619},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.212","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.212","pdf_url":"https://aclanthology.org/2025.findings-acl.212.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: ACL 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-148817","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-148817","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.212","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.212","pdf_url":"https://aclanthology.org/2025.findings-acl.212.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: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888716.pdf","grobid_xml":"https://content.openalex.org/works/W4412888716.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"rapid":[1],"development":[2],"of":[3,56,69,75,118],"LLMs":[4,16],"has":[5],"sparked":[6],"extensive":[7],"research":[8],"into":[9],"their":[10],"factual":[11],"knowledge.Current":[12],"works":[13],"find":[14,135],"that":[15,123,136],"fall":[17],"short":[18],"on":[19,153],"questions":[20,30,147,163],"around":[21],"low-frequency":[22,59,132,173],"entities.However,":[23],"such":[24,80,162],"proofs":[25],"are":[26],"unreliable":[27],"since":[28],"the":[29,67,73,77,85,150],"can":[31,138],"differ":[32],"not":[33],"only":[34,84,171],"in":[35,40,72],"entity":[36,86],"frequency":[37,71],"but":[38],"also":[39],"difficulty":[41],"themselves.So":[42],"we":[43,91,134,155],"introduce":[44],"COMPARISONQA":[45],"benchmark,":[46],"containing":[47,170],"283K":[48],"abstract":[49],"questions,":[50],"each":[51],"instantiated":[52],"by":[53],"a":[54,62,81,99,115,166],"pair":[55,82],"high-frequency":[57],"and":[58,95,145],"entities.It":[60],"ensures":[61],"controllable":[63],"comparison":[64],"to":[65,97,102,108,141,160,164],"study":[66],"role":[68],"knowledge":[70,105],"performance":[74],"LLMs.Because":[76],"difference":[78],"between":[79],"is":[83,114],"with":[87],"different":[88],"frequencies.In":[89],"addition,":[90],"use":[92],"both":[93],"correctness":[94],"uncertainty":[96,137],"develop":[98],"two-round":[100],"method":[101,159],"evaluate":[103],"LLMs'":[104],"robustness.It":[106],"aims":[107],"avoid":[109],"possible":[110],"semantic":[111],"shortcuts":[112],"which":[113],"serious":[116],"problem":[117],"current":[119],"QA":[120],"study.Experiments":[121],"reveal":[122],"LLMs,":[124],"including":[125],"GPT-4o,":[126],"exhibit":[127],"particularly":[128],"low":[129],"robustness":[130],"regarding":[131],"knowledge.Besides,":[133],"be":[139],"used":[140],"effectively":[142],"identify":[143],"high-quality":[144],"shortcut-free":[146],"while":[148],"maintaining":[149],"data":[151],"size.Based":[152],"this,":[154],"propose":[156],"an":[157],"automatic":[158],"select":[161],"form":[165],"subset":[167],"called":[168],"COMPARISONQA-Hard,":[169],"hard":[172],"questions.":[174],"1":[175,176],"https://github.com/":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}