{"id":"https://openalex.org/W4416036039","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.126","title":"Dynamic Evaluation for Oversensitivity in LLMs","display_name":"Dynamic Evaluation for Oversensitivity in LLMs","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036039","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.126"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.126","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.126","pdf_url":"https://aclanthology.org/2025.findings-emnlp.126.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.126.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120308982","display_name":"Sophia Xiao Pu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sophia Xiao Pu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120308983","display_name":"Sitao Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sitao Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327826","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-7467-6060"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Eric Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100702485","display_name":"William Yang Wang","orcid":"https://orcid.org/0000-0001-6153-8240"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Yang Wang","raw_affiliation_strings":["University of California , Santa Barbara"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Santa Barbara","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23106405,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2337","last_page":"2344"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.05490000173449516,"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"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.05490000173449516,"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/T11236","display_name":"Control Systems and Identification","score":0.0430000014603138,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.038600001484155655,"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/construct","display_name":"Construct (python library)","score":0.7537000179290771},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6628999710083008},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6611999869346619},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.39570000767707825}],"concepts":[{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.7537000179290771},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6628999710083008},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6611999869346619},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6432999968528748},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.357699990272522},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3474999964237213},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32260000705718994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31360000371932983},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29919999837875366},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.26330000162124634},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.126","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.126","pdf_url":"https://aclanthology.org/2025.findings-emnlp.126.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"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.126","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.126","pdf_url":"https://aclanthology.org/2025.findings-emnlp.126.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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036039.pdf","grobid_xml":"https://content.openalex.org/works/W4416036039.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Oversensitivity":[0],"occurs":[1],"when":[2],"language":[3],"models":[4,38,109],"defensively":[5],"reject":[6],"prompts":[7],"that":[8,33,54,79,113],"are":[9],"actually":[10],"benign.This":[11],"behavior":[12],"not":[13],"only":[14],"disrupts":[15],"user":[16],"interactions":[17],"but":[18],"also":[19],"obscures":[20],"the":[21],"boundary":[22],"between":[23],"harmful":[24],"and":[25,44,64,96],"harmless":[26],"content.Existing":[27],"benchmarks":[28],"rely":[29],"on":[30,71,99],"static":[31,114],"datasets":[32,82,115],"degrade":[34],"over":[35],"time":[36],"as":[37,108],"evolve,":[39],"leading":[40],"to":[41],"data":[42],"contamination":[43],"diminished":[45],"evaluative":[46],"power.To":[47],"address":[48],"this,":[49],"we":[50,74],"develop":[51],"a":[52,77,94],"framework":[53],"dynamically":[55],"generates":[56],"model-specific":[57],"challenging":[58],"datasets,":[59],"capturing":[60],"emerging":[61],"defensive":[62,106],"patterns":[63],"aligning":[65],"with":[66],"each":[67],"model's":[68],"unique":[69],"behavior.Building":[70],"this":[72],"approach,":[73],"construct":[75],"OVERBENCH,":[76],"benchmark":[78],"aggregates":[80],"these":[81],"across":[83],"diverse":[84],"LLM":[85],"families,":[86],"encompassing":[87],"450,000":[88],"samples":[89],"from":[90],"25":[91],"models.OVERBENCH":[92],"provides":[93],"dynamic":[95],"evolving":[97],"perspective":[98],"oversensitivity,":[100],"allowing":[101],"for":[102],"continuous":[103],"monitoring":[104],"of":[105],"triggers":[107],"advance,":[110],"highlighting":[111],"vulnerabilities":[112],"overlook.":[116],"1":[117]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}