{"id":"https://openalex.org/W4412889497","doi":"https://doi.org/10.18653/v1/2025.acl-short.82","title":"Can LLMs Generate High-Quality Test Cases for Algorithm Problems? TestCase-Eval: A Systematic Evaluation of Fault Coverage and Exposure","display_name":"Can LLMs Generate High-Quality Test Cases for Algorithm Problems? TestCase-Eval: A Systematic Evaluation of Fault Coverage and Exposure","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889497","doi":"https://doi.org/10.18653/v1/2025.acl-short.82"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-short.82","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-short.82","pdf_url":"https://aclanthology.org/2025.acl-short.82.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-short.82.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zheyuan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheyuan Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110176590","display_name":"Zexi Kuang","orcid":"https://orcid.org/0000-0001-6181-3425"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zexi Kuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020783379","display_name":"Xue Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue Xia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103004488","display_name":"Yilun Zhao","orcid":"https://orcid.org/0000-0002-7470-6124"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yilun Zhao","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":1.2703,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77761972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1050","last_page":"1063"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9861999750137329,"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"}},"topics":[{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9861999750137329,"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/T10260","display_name":"Software Engineering Research","score":0.9585000276565552,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9280999898910522,"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/computer-science","display_name":"Computer science","score":0.5925618410110474},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.5621459484100342},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5552805066108704},{"id":"https://openalex.org/keywords/fault-coverage","display_name":"Fault coverage","score":0.5349143147468567},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5295228362083435},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.3775769770145416},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33615630865097046},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13947486877441406}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5925618410110474},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.5621459484100342},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5552805066108704},{"id":"https://openalex.org/C126953365","wikidata":"https://www.wikidata.org/wiki/Q5438152","display_name":"Fault coverage","level":3,"score":0.5349143147468567},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5295228362083435},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.3775769770145416},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33615630865097046},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13947486877441406},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134146338","wikidata":"https://www.wikidata.org/wiki/Q1815901","display_name":"Electronic circuit","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-short.82","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-short.82","pdf_url":"https://aclanthology.org/2025.acl-short.82.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-short.82","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-short.82","pdf_url":"https://aclanthology.org/2025.acl-short.82.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889497.pdf","grobid_xml":"https://content.openalex.org/works/W4412889497.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W641782856","https://openalex.org/W4376453582","https://openalex.org/W24443521","https://openalex.org/W3147033875","https://openalex.org/W2471323292","https://openalex.org/W2296759459","https://openalex.org/W2045139758","https://openalex.org/W1568390478","https://openalex.org/W4205202004","https://openalex.org/W2764722704"],"abstract_inverted_index":{"We":[0],"introduce":[1],"TestCase-Eval,":[2,85],"a":[3,47,62,68,74],"new":[4],"benchmark":[5],"for":[6,98],"systematic":[7],"evaluation":[8],"of":[9,50,77],"LLMs":[10,59,83],"in":[11,93],"test-case":[12],"generation.TestCase-Eval":[13],"includes":[14],"500":[15],"algorithm":[16,99],"problems":[17],"and":[18,45,81,91],"100,000":[19],"human-crafted":[20],"solutions":[21],"from":[22],"the":[23],"Codeforces":[24],"platform.It":[25],"focuses":[26],"on":[27,84],"two":[28],"pivotal":[29],"tasks:":[30],"(1)":[31],"Fault":[32,54],"Coverage,":[33],"which":[34,56],"measures":[35],"how":[36],"well":[37],"LLM-generated":[38],"test":[39,64,96],"sets":[40],"probe":[41],"diverse":[42],"input":[43,65],"scenarios":[44],"cover":[46],"wide":[48],"range":[49],"potential":[51],"failure":[52],"modes.(2)":[53],"Exposure,":[55],"evaluates":[57],"whether":[58],"can":[60],"craft":[61],"tailored":[63],"that":[66],"reveals":[67],"specific":[69],"incorrect":[70],"code":[71],"implementation.We":[72],"provide":[73],"comprehensive":[75],"assessment":[76],"19":[78],"stateof-the-art":[79],"open-source":[80],"proprietary":[82],"offering":[86],"insights":[87],"into":[88],"their":[89],"strengths":[90],"limitations":[92],"generating":[94],"effective":[95],"cases":[97],"problems.":[100]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
