{"id":"https://openalex.org/W4396833505","doi":"https://doi.org/10.1145/3613904.3642216","title":"EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteria","display_name":"EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteria","publication_year":2024,"publication_date":"2024-05-11","ids":{"openalex":"https://openalex.org/W4396833505","doi":"https://doi.org/10.1145/3613904.3642216"},"language":"en","primary_location":{"id":"doi:10.1145/3613904.3642216","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613904.3642216","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613904.3642216","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3613904.3642216","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021946392","display_name":"Tae Soo Kim","orcid":"https://orcid.org/0000-0001-9078-6032"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tae Soo Kim","raw_affiliation_strings":["School of Computing, KAIST, Korea, Republic of"],"raw_orcid":"https://orcid.org/0000-0001-9078-6032","affiliations":[{"raw_affiliation_string":"School of Computing, KAIST, Korea, Republic of","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101464055","display_name":"Yoonjoo Lee","orcid":"https://orcid.org/0000-0001-7491-986X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yoonjoo Lee","raw_affiliation_strings":["School of Computing, KAIST, Korea, Republic of"],"raw_orcid":"https://orcid.org/0000-0001-7491-986X","affiliations":[{"raw_affiliation_string":"School of Computing, KAIST, Korea, Republic of","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076515960","display_name":"Jamin Shin","orcid":"https://orcid.org/0000-0002-4604-7299"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jamin Shin","raw_affiliation_strings":["NAVER AI Lab, Korea, Republic of"],"raw_orcid":"https://orcid.org/0000-0002-4604-7299","affiliations":[{"raw_affiliation_string":"NAVER AI Lab, Korea, Republic of","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062848438","display_name":"Young\u2010Ho Kim","orcid":"https://orcid.org/0000-0002-2681-2774"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Young-Ho Kim","raw_affiliation_strings":["NAVER AI Lab, Korea, Republic of"],"raw_orcid":"https://orcid.org/0000-0002-2681-2774","affiliations":[{"raw_affiliation_string":"NAVER AI Lab, Korea, Republic of","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079709359","display_name":"Juho Kim","orcid":"https://orcid.org/0000-0001-6348-4127"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juho Kim","raw_affiliation_strings":["School of Computing, KAIST, Korea, Republic of"],"raw_orcid":"https://orcid.org/0000-0001-6348-4127","affiliations":[{"raw_affiliation_string":"School of Computing, KAIST, Korea, Republic of","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":50.835,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.99890329,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9994000196456909,"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/T10260","display_name":"Software Engineering Research","score":0.9994000196456909,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.9936000108718872,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/formative-assessment","display_name":"Formative assessment","score":0.8382770419120789},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8246471881866455},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6351307034492493},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5265251398086548},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5034806132316589},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4286189675331116},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38283678889274597},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36197155714035034},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.34665706753730774},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.0885445773601532}],"concepts":[{"id":"https://openalex.org/C42525527","wikidata":"https://www.wikidata.org/wiki/Q1209955","display_name":"Formative assessment","level":2,"score":0.8382770419120789},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8246471881866455},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6351307034492493},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5265251398086548},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5034806132316589},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4286189675331116},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38283678889274597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36197155714035034},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.34665706753730774},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0885445773601532},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3613904.3642216","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613904.3642216","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613904.3642216","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3613904.3642216","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613904.3642216","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613904.3642216","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396833505.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2157289187","https://openalex.org/W2757211916","https://openalex.org/W2801702920","https://openalex.org/W2956281901","https://openalex.org/W3159259047","https://openalex.org/W3164854573","https://openalex.org/W3185341429","https://openalex.org/W3203321135","https://openalex.org/W3204393347","https://openalex.org/W3206420877","https://openalex.org/W4221143046","https://openalex.org/W4225012671","https://openalex.org/W4225165463","https://openalex.org/W4285113702","https://openalex.org/W4301393026","https://openalex.org/W4307475457","https://openalex.org/W4320342906","https://openalex.org/W4321161602","https://openalex.org/W4321455981","https://openalex.org/W4362454930","https://openalex.org/W4365597197","https://openalex.org/W4365601419","https://openalex.org/W4366548330","https://openalex.org/W4366550149","https://openalex.org/W4366729084","https://openalex.org/W4378908626","https://openalex.org/W4383679928","https://openalex.org/W4385571232","https://openalex.org/W4387801187","https://openalex.org/W4389519254","https://openalex.org/W4401042360"],"related_works":["https://openalex.org/W609482051","https://openalex.org/W3199325201","https://openalex.org/W2792035366","https://openalex.org/W4386050096","https://openalex.org/W2360976019","https://openalex.org/W2351166673","https://openalex.org/W2390109066","https://openalex.org/W2002537515","https://openalex.org/W2349355552","https://openalex.org/W2894473080"],"abstract_inverted_index":{"By":[0,69],"simply":[1],"composing":[2],"prompts,":[3,132],"developers":[4,21,37],"can":[5,76,135],"prototype":[6],"novel":[7],"generative":[8],"applications":[9],"with":[10,127],"Large":[11],"Language":[12],"Models":[13],"(LLMs).":[14],"To":[15],"refine":[16],"prototypes":[17],"into":[18],"products,":[19],"however,":[20],"must":[22],"iteratively":[23,59],"revise":[24],"prompts":[25,61,88,126],"by":[26,62],"evaluating":[27,43,63],"outputs":[28,44,65],"to":[29,82,109,138],"diagnose":[30],"weaknesses.":[31],"Formative":[32],"interviews":[33],"(N=8)":[34],"revealed":[35],"that":[36,105],"invest":[38],"significant":[39],"effort":[40],"in":[41,72,144],"manually":[42],"as":[45,120],"they":[46],"assess":[47],"context-specific":[48],"and":[49,92,123,142],"subjective":[50],"criteria.":[51,68],"We":[52],"present":[53],"EvalLM,":[54,106],"an":[55,84],"interactive":[56],"system":[57],"for":[58],"refining":[60],"multiple":[64],"on":[66,96],"user-defined":[67],"describing":[70],"criteria":[71],"natural":[73],"language,":[74],"users":[75],"employ":[77],"the":[78,97],"system\u2019s":[79],"LLM-based":[80],"evaluator":[81],"get":[83],"overview":[85],"of":[86],"where":[87],"excel":[89],"or":[90],"fail,":[91],"improve":[93],"these":[94],"based":[95],"evaluator\u2019s":[98],"feedback.":[99],"A":[100],"comparative":[101],"study":[102],"(N=12)":[103],"showed":[104],"when":[107],"compared":[108],"manual":[110],"evaluation,":[111],"helped":[112],"participants":[113],"compose":[114],"more":[115],"diverse":[116],"criteria,":[117],"examine":[118],"twice":[119],"many":[121],"outputs,":[122],"reach":[124],"satisfactory":[125],"59%":[128],"fewer":[129],"revisions.":[130],"Beyond":[131],"our":[133],"work":[134],"be":[136],"extended":[137],"augment":[139],"model":[140],"evaluation":[141],"alignment":[143],"specific":[145],"application":[146],"contexts.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":23},{"year":2025,"cited_by_count":47},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-13T07:54:00.901334","created_date":"2024-05-12T00:00:00"}
