{"id":"https://openalex.org/W7137998444","doi":"https://doi.org/10.1609/aaai.v40i20.38785","title":"Hide and Seek with LLMs: An Adversarial Game for Sneaky Error Generation and Self-Improving Diagnosis","display_name":"Hide and Seek with LLMs: An Adversarial Game for Sneaky Error Generation and Self-Improving Diagnosis","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137998444","doi":"https://doi.org/10.1609/aaai.v40i20.38785"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i20.38785","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i20.38785","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38785/42747","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38785/42747","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129654291","display_name":"Rui Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rui Zou","raw_affiliation_strings":["Renmin University of China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039345378","display_name":"Mengqi Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengqi Wei","raw_affiliation_strings":["Central China Normal University"],"affiliations":[{"raw_affiliation_string":"Central China Normal University","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129695493","display_name":"Yutao Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutao Zhu","raw_affiliation_strings":["Renmin University of China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125635347","display_name":"Jirong Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jirong Wen","raw_affiliation_strings":["Renmin University of China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129695741","display_name":"Xin Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Zhao","raw_affiliation_strings":["Renmin University of China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129745972","display_name":"Jing Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I158934434","display_name":"Zhongnan University of Economics and Law","ror":"https://ror.org/04yqxxq63","country_code":"CN","type":"education","lineage":["https://openalex.org/I158934434"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Chen","raw_affiliation_strings":["Zhongnan University of Economics and Law"],"affiliations":[{"raw_affiliation_string":"Zhongnan University of Economics and Law","institution_ids":["https://openalex.org/I158934434"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5129654291"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2194992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"20","first_page":"17327","last_page":"17335"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4377000033855438,"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":0.4377000033855438,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.12080000340938568,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.08100000023841858,"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/adversarial-system","display_name":"Adversarial system","score":0.9093000292778015},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6270999908447266},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5587000250816345},{"id":"https://openalex.org/keywords/hide-and-seek","display_name":"Hide and seek","score":0.43970000743865967},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.3765999972820282},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.32989999651908875}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9093000292778015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7633000016212463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6388000249862671},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6270999908447266},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5587000250816345},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5397999882698059},{"id":"https://openalex.org/C2994203483","wikidata":"https://www.wikidata.org/wiki/Q171957","display_name":"Hide and seek","level":2,"score":0.43970000743865967},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C2778403875","wikidata":"https://www.wikidata.org/wiki/Q20312394","display_name":"Adversarial machine learning","level":3,"score":0.2651999890804291}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i20.38785","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i20.38785","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38785/42747","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i20.38785","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i20.38785","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38785/42747","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1899978318","display_name":null,"funder_award_id":"L233008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137998444.pdf","grobid_xml":"https://content.openalex.org/works/W7137998444.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"excel":[4],"in":[5,57],"reasoning":[6,98,123],"and":[7,16,33,67,78,80,100,114,149],"generation":[8,77],"across":[9],"domains,":[10],"but":[11],"still":[12],"struggle":[13],"with":[14],"identifying":[15],"diagnosing":[17],"complex":[18],"errors.":[19,36],"This":[20],"stems":[21],"mainly":[22],"from":[23,35],"training":[24],"objectives":[25],"that":[26,126],"prioritize":[27],"correct":[28],"answers,":[29],"limiting":[30],"exposure":[31],"to":[32,42,104],"learning":[34],"While":[37],"recent":[38],"studies":[39],"have":[40],"begun":[41],"address":[43],"this":[44],"by":[45,94],"introducing":[46],"error":[47,76,112,130],"signals,":[48],"most":[49],"rely":[50],"on":[51,83,120],"shallow,":[52],"static":[53],"errors,":[54,99],"restricting":[55],"improvement":[56],"deep":[58],"diagnostic":[59,115,150],"ability.":[60],"To":[61],"overcome":[62],"this,":[63],"we":[64],"propose":[65],"Hide":[66],"Seek":[68],"Game":[69],"(HSG),":[70],"a":[71,143,153],"dynamic":[72],"adversarial":[73,89,109],"framework":[74],"for":[75,155],"diagnosis,":[79,131],"evaluate":[81],"it":[82],"mathematical":[84,122],"problem-solving.":[85],"HSG":[86,127],"involves":[87],"two":[88],"roles:":[90],"Sneaky,":[91],"which":[92,102],"hides":[93],"generating":[95],"subtle,":[96],"deceptive":[97,147],"Diagnosis,":[101],"seeks":[103],"accurately":[105],"detect":[106],"them.":[107],"Through":[108],"co-evolution,":[110],"both":[111],"stealth":[113],"precision":[116],"are":[117],"enhanced.":[118],"Experiments":[119],"three":[121],"datasets":[124],"demonstrate":[125],"significantly":[128],"boosts":[129],"achieving":[132],"16.8%-31.4%":[133],"higher":[134],"accuracy":[135],"than":[136],"baselines":[137],"like":[138],"GPT-4o.":[139],"We":[140],"also":[141],"release":[142],"challenging":[144],"dataset":[145],"of":[146],"errors":[148],"annotations":[151],"as":[152],"benchmark":[154],"future":[156],"research.":[157]},"counts_by_year":[],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2026-03-18T00:00:00"}