{"id":"https://openalex.org/W4399759052","doi":"https://doi.org/10.34727/2024/isbn.978-3-85448-065-5_19","title":"Evaluating LLM-driven User-Intent Formalization for Verification-Aware Languages","display_name":"Evaluating LLM-driven User-Intent Formalization for Verification-Aware Languages","publication_year":2024,"publication_date":"2024-06-14","ids":{"openalex":"https://openalex.org/W4399759052","doi":"https://doi.org/10.34727/2024/isbn.978-3-85448-065-5_19"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.09757","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.09757","pdf_url":"https://arxiv.org/pdf/2406.09757","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.09757","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041084431","display_name":"Shuvendu K. Lahiri","orcid":"https://orcid.org/0000-0002-4446-4777"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lahiri, Shuvendu K.","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5041084431"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5387,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70907852,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.9911999702453613,"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"}},"topics":[{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.9911999702453613,"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.9710999727249146,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.9674999713897705,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.7025818824768066},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.456290066242218},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.4271126985549927},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3327428698539734}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7025818824768066},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.456290066242218},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4271126985549927},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3327428698539734}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2406.09757","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.09757","pdf_url":"https://arxiv.org/pdf/2406.09757","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.09757","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.09757","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.34727/2024/isbn.978-3-85448-065-5_19","is_oa":true,"landing_page_url":"https://doi.org/10.34727/2024/isbn.978-3-85448-065-5_19","pdf_url":null,"source":{"id":"https://openalex.org/S4306400493","display_name":"reposiTUm (TU Wien)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145847075","host_organization_name":"TU Wien","host_organization_lineage":["https://openalex.org/I145847075"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.09757","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.09757","pdf_url":"https://arxiv.org/pdf/2406.09757","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399759052.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Verification-aware":[0],"programming":[1,123],"languages":[2,135],"such":[3,126],"as":[4,50],"Dafny":[5,204],"and":[6,13,67,92,103,142,254],"F*":[7],"provide":[8,178],"means":[9],"to":[10,133,161,177,230,233,247],"formally":[11],"specify":[12],"prove":[14],"properties":[15],"of":[16,22,38,42,77,172,186,203,251,260],"a":[17,27,51,71,112,200,244,252],"program.":[18],"Although":[19],"the":[20,40,43,68,75,87,116,163,184,207,216,235,249,258],"problem":[21,120,259],"checking":[23],"an":[24,127,167,179],"implementation":[25],"against":[26],"specification":[28,69],"can":[29],"be":[30,147,231],"defined":[31],"mechanically,":[32],"there":[33],"is":[34,55,60,70,219],"no":[35],"algorithmic":[36],"way":[37],"ensuring":[39],"correctness":[41],"{\\it":[44,62,117,173],"user-intent":[45,118,261],"formalization":[46,262],"for":[47,106,114,121,182,188,206,257,263],"programs},":[48],"expressed":[49,61],"formal":[52,72,93,225],"specification.":[53],"This":[54],"because":[56],"intent":[57,91],"or":[58],"requirement":[59],"informally}":[63],"in":[64,98],"natural":[65],"language":[66,79],"artefact.":[73],"Despite,":[74],"advent":[76],"large":[78,99],"models":[80],"(LLMs)":[81],"has":[82,110],"made":[83],"tremendous":[84],"strides":[85],"bridging":[86],"gap":[88],"between":[89],"informal":[90],"program":[94,157],"implementations":[95],"recently,":[96],"driven":[97],"parts":[100],"by":[101],"benchmarks":[102],"automated":[104,195],"metrics":[105],"evaluation.":[107],"Recent":[108],"work":[109,153,242],"proposed":[111],"framework":[113],"evaluating":[115,183],"formalization}":[119],"mainstream":[122],"languages~\\cite{endres-fse24}.":[124],"However,":[125],"approach":[128,171],"does":[129],"not":[130,220],"readily":[131],"extend":[132],"verification-aware":[134,189],"that":[136,145,193,228],"support":[137],"rich":[138],"specifications":[139,187,205],"(using":[140],"quantifiers":[141],"ghost":[143],"variables)":[144],"cannot":[146],"evaluated":[148],"through":[149],"dynamic":[150],"execution.":[151],"Previous":[152],"also":[154,223],"required":[155],"generating":[156],"mutants":[158],"using":[159],"LLMs":[160],"create":[162],"benchmark.":[164],"We":[165,191,222,239],"advocate":[166],"alternate,":[168],"perhaps":[169],"simpler":[170],"symbolically":[174],"testing":[175],"specifications}":[176],"intuitive":[180],"metric":[181,196],"quality":[185],"languages.":[190],"demonstrate":[192],"our":[194,241],"agrees":[197],"closely":[198],"on":[199],"human-labeled":[201],"dataset":[202],"popular":[208],"MBPP":[209],"code-generation":[210],"benchmark,":[211],"yet":[212],"demonstrates":[213],"cases":[214],"where":[215],"human":[217],"labeling":[218],"perfect.":[221],"outline":[224],"verification":[226],"challenges":[227],"need":[229],"addressed":[232],"apply":[234],"technique":[236],"more":[237],"widely.":[238],"believe":[240],"provides":[243],"stepping":[245],"stone":[246],"enable":[248],"establishment":[250],"benchmark":[253],"research":[255],"agenda":[256],"programs.":[264]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2024-06-18T00:00:00"}
