{"id":"https://openalex.org/W7169622334","doi":"https://doi.org/10.1145/3803437.3805260","title":"Understanding and Mitigating Hallucinations in Industrial LLM-based Unit Test Generation","display_name":"Understanding and Mitigating Hallucinations in Industrial LLM-based Unit Test Generation","publication_year":2026,"publication_date":"2026-07-05","ids":{"openalex":"https://openalex.org/W7169622334","doi":"https://doi.org/10.1145/3803437.3805260"},"language":null,"primary_location":{"id":"doi:10.1145/3803437.3805260","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3803437.3805260","pdf_url":null,"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 34th ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3803437.3805260","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005049605","display_name":"Yanlun Tu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanlun Tu","raw_affiliation_strings":["Ant Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3632-5339","affiliations":[{"raw_affiliation_string":"Ant Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141066296","display_name":"Ziyue Zhou","orcid":"https://orcid.org/0009-0001-6608-2358"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyue Zhou","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0001-6608-2358","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141055349","display_name":"Cheng Xu","orcid":"https://orcid.org/0009-0001-0067-2929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng Xu","raw_affiliation_strings":["Ant Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-0067-2929","affiliations":[{"raw_affiliation_string":"Ant Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029629116","display_name":"Jingling Sun","orcid":"https://orcid.org/0000-0002-8437-0687"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingling Sun","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-8437-0687","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141063863","display_name":"Shuai Feng","orcid":"https://orcid.org/0009-0004-2904-6640"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai Feng","raw_affiliation_strings":["Ant Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-2904-6640","affiliations":[{"raw_affiliation_string":"Ant Group, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100722691","display_name":"Chengyu Zhang","orcid":"https://orcid.org/0000-0002-7285-289X"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chengyu Zhang","raw_affiliation_strings":["Loughborough University, Loughborough, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-7285-289X","affiliations":[{"raw_affiliation_string":"Loughborough University, Loughborough, United Kingdom","institution_ids":["https://openalex.org/I143804889"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"892","last_page":"902"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5881999731063843},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5130000114440918},{"id":"https://openalex.org/keywords/unit-testing","display_name":"Unit testing","score":0.4984999895095825},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.46239998936653137},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.38850000500679016},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.38690000772476196},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3695000112056732},{"id":"https://openalex.org/keywords/test-strategy","display_name":"Test strategy","score":0.32170000672340393}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6560999751091003},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5881999731063843},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5130000114440918},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.5044999718666077},{"id":"https://openalex.org/C148027188","wikidata":"https://www.wikidata.org/wiki/Q907375","display_name":"Unit testing","level":3,"score":0.4984999895095825},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.46239998936653137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42489999532699585},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34439998865127563},{"id":"https://openalex.org/C188598960","wikidata":"https://www.wikidata.org/wiki/Q7705805","display_name":"Test strategy","level":3,"score":0.32170000672340393},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.31630000472068787},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C165825675","wikidata":"https://www.wikidata.org/wiki/Q1399743","display_name":"Model-based testing","level":4,"score":0.3111000061035156},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.29679998755455017},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.26100000739097595}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3803437.3805260","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3803437.3805260","pdf_url":null,"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 34th ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3803437.3805260","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3803437.3805260","pdf_url":null,"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 34th ACM International Conference on the Foundations of Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2101512909","https://openalex.org/W2107729695","https://openalex.org/W2109276114","https://openalex.org/W2122205205","https://openalex.org/W2156723666","https://openalex.org/W2247455710","https://openalex.org/W2547621596","https://openalex.org/W2788064332","https://openalex.org/W2789416185","https://openalex.org/W2963723316","https://openalex.org/W4237492309","https://openalex.org/W4288084466","https://openalex.org/W4389104713","https://openalex.org/W4399213400","https://openalex.org/W4400484392","https://openalex.org/W4400484796","https://openalex.org/W4400582690","https://openalex.org/W4403536268","https://openalex.org/W4403536388","https://openalex.org/W4404534210","https://openalex.org/W4411552855","https://openalex.org/W4413267861","https://openalex.org/W4413267891","https://openalex.org/W4413267897","https://openalex.org/W4413360274"],"related_works":[],"abstract_inverted_index":{"Unit":[0],"testing":[1],"plays":[2],"a":[3,111],"critical":[4],"role":[5],"in":[6,12,48],"ensuring":[7],"software":[8],"quality":[9],"and":[10,53,67,103,118,126,142,162],"reliability":[11],"large-scale":[13],"industrial":[14],"environments.":[15],"While":[16],"Large":[17],"Language":[18],"Models":[19],"(LLMs)":[20],"offer":[21],"promising":[22],"automated":[23,86],"test":[24,89],"generation":[25,90],"capabilities,":[26],"their":[27],"practical":[28],"deployment":[29],"faces":[30],"significant":[31],"challenges":[32],"due":[33],"to":[34,114],"hallucination":[35],"problems.":[36],"In":[37,151],"this":[38],"paper,":[39],"we":[40,82],"analyze":[41],"compilation":[42],"failures":[43],"from":[44,71],"LLM-generated":[45],"unit":[46,88],"tests":[47],"Ant":[49,131,181],"Group's":[50,132],"production":[51],"systems":[52],"identify":[54],"two":[55],"fundamental":[56],"types":[57,96],"of":[58,97],"hallucinations:":[59],"extrinsic":[60],"hallucinations":[61,69,98],"caused":[62],"by":[63],"insufficient":[64],"contextual":[65],"information":[66],"intrinsic":[68],"stemming":[70],"model":[72],"limitations":[73],"even":[74],"with":[75,189],"adequate":[76],"context.":[77],"To":[78],"address":[79],"these":[80],"issues,":[81],"propose":[83],"DEHALL,":[84],"an":[85,184],"end-to-end":[87],"tool":[91],"that":[92,136],"systematically":[93],"mitigates":[94],"both":[95],"through":[99],"comprehensive":[100],"context":[101,117],"construction":[102],"targeted":[104],"static":[105],"analysis-based":[106],"repair.":[107],"Our":[108],"approach":[109],"builds":[110],"heterogeneous":[112],"graph":[113],"capture":[115],"relevant":[116],"employs":[119],"specialized":[120],"repair":[121],"mechanisms":[122],"for":[123],"import,":[124],"field,":[125],"method":[127],"issues.":[128],"Evaluation":[129],"on":[130,160,193],"internal":[133],"datasets":[134],"reveals":[135],"DEHALL":[137,171],"achieves":[138],"71.56%":[139],"line":[140],"coverage":[141,161],"67.18%":[143],"branch":[144],"coverage,":[145],"significantly":[146],"outperforming":[147],"vanilla":[148],"LLM":[149],"approaches.":[150,170],"the":[152],"public":[153],"benchmarks,":[154],"it":[155],"also":[156],"shows":[157],"better":[158,163],"performance":[159],"defect":[164],"detection":[165],"capability":[166],"than":[167],"previous":[168],"state-of-the-art":[169],"has":[172],"been":[173],"successfully":[174],"deployed":[175],"across":[176],"multiple":[177],"business":[178],"domains":[179],"at":[180],"Group,":[182],"achieving":[183],"81%":[185],"developer":[186],"adoption":[187],"rate":[188],"positive":[190],"user":[191],"feedback":[192],"productivity":[194],"improvements.":[195]},"counts_by_year":[],"updated_date":"2026-07-18T05:58:53.570196","created_date":"2026-07-18T00:00:00"}