{"id":"https://openalex.org/W4412944485","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1357","title":"LLM-as-an-Interviewer: Beyond Static Testing Through Dynamic LLM Evaluation","display_name":"LLM-as-an-Interviewer: Beyond Static Testing Through Dynamic LLM Evaluation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944485","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1357"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1357","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1357","pdf_url":"https://aclanthology.org/2025.findings-acl.1357.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.1357.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115505085","display_name":"Eunsu Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eunsu Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115505086","display_name":"Juyoung Suk","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juyoung Suk","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014381991","display_name":"Seungone Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seungone Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115505087","display_name":"Niklas Muennighoff","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niklas Muennighoff","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115505088","display_name":"Dongkwan Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongkwan Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5115505089","display_name":"Alice Oh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alice Oh","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":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"26456","last_page":"26493"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14330","display_name":"Library Science and Information Systems","score":0.8952999711036682,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T14330","display_name":"Library Science and Information Systems","score":0.8952999711036682,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.8863999843597412,"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/T13643","display_name":"Artificial Intelligence in Law","score":0.8834999799728394,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6546702980995178},{"id":"https://openalex.org/keywords/interview","display_name":"Interview","score":0.5336469411849976},{"id":"https://openalex.org/keywords/dynamic-testing","display_name":"Dynamic testing","score":0.46312057971954346},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.24324846267700195},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.06592985987663269}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6546702980995178},{"id":"https://openalex.org/C24845683","wikidata":"https://www.wikidata.org/wiki/Q178651","display_name":"Interview","level":2,"score":0.5336469411849976},{"id":"https://openalex.org/C198824145","wikidata":"https://www.wikidata.org/wiki/Q442770","display_name":"Dynamic testing","level":2,"score":0.46312057971954346},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.24324846267700195},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.06592985987663269},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1357","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1357","pdf_url":"https://aclanthology.org/2025.findings-acl.1357.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"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1357","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1357","pdf_url":"https://aclanthology.org/2025.findings-acl.1357.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":[{"id":"https://openalex.org/F4320322030","display_name":"Ministry of Science, ICT and Future Planning","ror":"https://ror.org/032e49973"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944485.pdf","grobid_xml":"https://content.openalex.org/works/W4412944485.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/W4235390613","https://openalex.org/W4242454971","https://openalex.org/W2074621494","https://openalex.org/W4249866375","https://openalex.org/W2073189711","https://openalex.org/W2481553649","https://openalex.org/W4255408515"],"abstract_inverted_index":{"We":[0],"introduce":[1],"LLM-AS-AN-INTERVIEWER,":[2],"a":[3,130,141,159],"novel":[4],"paradigm":[5],"for":[6,165],"evaluating":[7],"large":[8],"language":[9],"models":[10,58],"(LLMs).This":[11],"approach":[12],"leverages":[13],"multi-turn":[14],"interactions":[15],"where":[16],"the":[17,30,33,36,38,52,60,69,78,117,124,134,145,169],"LLM":[18,39,75],"interviewer":[19,40],"actively":[20],"provides":[21,72],"feedback":[22],"on":[23,59,168],"responses":[24],"and":[25,63,86,111,129,137],"poses":[26],"follow-up":[27,90],"questions":[28],"to":[29,44,55,84,88],"evaluated":[31],"LLM.At":[32],"start":[34],"of":[35,80,103,133,144,154],"interview,":[37],"dynamically":[41],"modifies":[42],"datasets":[43],"generate":[45],"initial":[46,81],"questions,":[47],"mitigating":[48],"data":[49],"contamination.We":[50],"apply":[51],"LLM-as-an-Interviewer":[53],"framework":[54,70,98],"evaluate":[56],"six":[57],"reasoning,":[61],"factuality":[62],"instruction-following":[64],"tasks.Our":[65],"results":[66],"show":[67],"that":[68],"effectively":[71],"insights":[73,122],"into":[74],"performance,":[76],"including":[77,108],"quality":[79],"responses,":[82],"adaptability":[83],"feedback,":[85],"ability":[87],"address":[89],"queries":[91],"like":[92,106],"clarification":[93],"or":[94],"additional":[95],"knowledge":[96],"requests.The":[97],"also":[99],"addresses":[100],"key":[101],"limitations":[102],"conventional":[104],"methods":[105],"LLM-as-a-Judge,":[107],"verbosity":[109],"bias":[110],"inconsistency":[112],"across":[113],"runs.Finally,":[114],"we":[115],"propose":[116],"Interview":[118],"Report,":[119],"which":[120],"aggregates":[121],"from":[123],"interview":[125],"process,":[126],"providing":[127],"examples":[128],"comprehensive":[131],"analysis":[132],"LLM's":[135],"strengths":[136],"weaknesses.This":[138],"report":[139],"offers":[140],"detailed":[142],"snapshot":[143],"model's":[146],"realworld":[147],"applicability":[148],"12":[149],".":[150],"MT-bench":[151],"Failure":[152],"Example":[153],"DeepseekQuestion-Turn-1:":[155],"Help":[156],"me":[157],"construct":[158],"catchy,":[160],"yet":[161],"scientifically":[162],"accurate,":[163],"headline":[164],"an":[166],"article":[167],"(...":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}