{"id":"https://openalex.org/W7217231950","doi":null,"title":"Code Without Context: Can We Trust LLMs to Test Software from Informal Descriptions?","display_name":"Code Without Context: Can We Trust LLMs to Test Software from Informal Descriptions?","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7217231950"},"language":"en","primary_location":{"id":"pmh:oai:rua.ua.es:10045/170209","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/10045/170209","pdf_url":null,"source":{"id":"https://openalex.org/S4306400975","display_name":"RUA, Repositorio Institucional de la Universidad de Alicante (Universidad de Alicante)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I130194489","host_organization_name":"University of Alicante","host_organization_lineage":["https://openalex.org/I130194489"],"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":"info:eu-repo/semantics/conferenceObject"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/10045/170209","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124381452","display_name":"Amneh Al Abdi","orcid":"https://orcid.org/0009-0007-1795-431X","observed_orcids":["https://orcid.org/0009-0007-1795-431X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Al Abdi, Amneh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5155224389","display_name":"Saad Ezzini","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ezzini, Saad","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9643999934196472,"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":0.9643999934196472,"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":0.031599998474121094,"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/T10028","display_name":"Topic Modeling","score":0.000699999975040555,"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/large-language-models","display_name":"large language models","score":0.8740000128746033},{"id":"https://openalex.org/keywords/automatic-test-generation","display_name":"automated test generation","score":0.9340000152587891},{"id":"https://openalex.org/keywords/llm-safety","display_name":"LLM safety","score":0.4300000071525574},{"id":"https://openalex.org/keywords/python","display_name":"Python","score":0.3160000145435333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7182000279426575},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6230000257492065},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.504800021648407},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.49380001425743103},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.46299999952316284},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.43389999866485596},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4307999908924103},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4198000133037567},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4196000099182129},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.4194999933242798},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.4115999937057495},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40950000286102295},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.36250001192092896},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3296000063419342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3009999990463257},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.28459998965263367},{"id":"https://openalex.org/C151552104","wikidata":"https://www.wikidata.org/wiki/Q7705809","display_name":"Test suite","level":4,"score":0.27149999141693115},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C67463725","wikidata":"https://www.wikidata.org/wiki/Q17081452","display_name":"Natural language programming","level":5,"score":0.257999986410141},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2565999925136566}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:rua.ua.es:10045/170209","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/10045/170209","pdf_url":null,"source":{"id":"https://openalex.org/S4306400975","display_name":"RUA, Repositorio Institucional de la Universidad de Alicante (Universidad de Alicante)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I130194489","host_organization_name":"University of Alicante","host_organization_lineage":["https://openalex.org/I130194489"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:rua.ua.es:10045/170209","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/10045/170209","pdf_url":null,"source":{"id":"https://openalex.org/S4306400975","display_name":"RUA, Repositorio Institucional de la Universidad de Alicante (Universidad de Alicante)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I130194489","host_organization_name":"University of Alicante","host_organization_lineage":["https://openalex.org/I130194489"],"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":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4402571250","https://openalex.org/W4403795814","https://openalex.org/W4409647619","https://openalex.org/W4414976378","https://openalex.org/W4414995150","https://openalex.org/W7125013018","https://openalex.org/W4413240361","https://openalex.org/W7117735017","https://openalex.org/W4417338309","https://openalex.org/W7092191125"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,12,48,56,96,140,156,195,243],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"have":[7,193],"shown":[8],"their":[9,103],"strong":[10],"abilities":[11],"several":[13,22],"tasks,":[14],"such":[15,24],"as":[16,25],"text":[17],"understanding":[18,104,196],"and":[19,45,77,123,138,145,164,168,176,179,204,211,235,246],"generation.":[20],"In":[21],"domains,":[23],"software":[26],"engineering,":[27],"LLMs":[28,88,234],"are":[29,53,62,132],"increasingly":[30],"used":[31,116],"to":[32,74,86,117,229],"automate":[33],"related":[34,73,228],"tasks.":[35],"However,":[36],"LLM-generated":[37],"outputs":[38],"still":[39],"raise":[40,226],"major":[41],"concerns":[42,52,227],"about":[43],"robustness":[44],"reliability,":[46],"especially":[47,54,242],"real-world":[49],"use.":[50],"These":[51,223],"important":[55],"cases":[57,131],"where":[58],"the":[59,75,90,197,209,230],"available":[60],"inputs":[61],"informal":[63,200],"natural":[64,201,220],"language":[65,202,221],"rather":[66],"than":[67],"structured":[68],"inputs,":[69],"which":[70],"raises":[71],"issues":[72],"trustworthiness":[76],"potential":[78,236],"risks":[79],"of":[80,105,111,142,158,186,199,213,233],"LLM":[81],"outputs.":[82],"This":[83],"paper":[84],"aims":[85],"evaluate":[87,118],"for":[89,166],"automated":[91,244],"test":[92,130,215],"case":[93,216],"generation":[94,217],"task":[95],"a":[97,119,124],"weaker-input":[98],"setting,":[99],"relying":[100],"solely":[101],"on":[102,134],"these":[106],"unstructured":[107],"inputs.":[108],"A":[109],"dataset":[110],"191":[112],"programming":[113],"problems":[114],"is":[115],"general-purpose":[120],"LLM,":[121,126],"GPT-5-mini,":[122],"code-specialized":[125],"Qwen2.5-Coder-7B.":[127],"The":[128,149,184],"generated":[129],"executed":[133],"reference":[135],"Python":[136],"solutions":[137],"evaluated":[139],"terms":[141,157],"both":[143,159,191],"test-level":[144,167,178],"problem-level":[146,180],"pass":[147,181],"rates.":[148],"results":[150,185,224],"show":[151],"that":[152,190],"GPT-5-mini":[153],"outperformed":[154],"Qwen2.5-Coder-7B":[155,172],"performance":[160],"metrics,":[161],"with":[162],"63.72%":[163],"59.16%":[165],"problem-level,":[169],"respectively,":[170],"while":[171],"achieves":[173],"only":[174,219],"21.62%":[175],"2.09%":[177],"rates,":[182],"respectively.":[183],"this":[187],"study":[188],"indicate":[189],"models":[192],"limitations":[194,212],"semantics":[198],"descriptions,":[203],"provide":[205],"early":[206],"insight":[207],"into":[208],"feasibility":[210],"LLM-based":[214],"using":[218],"descriptions.":[222],"also":[225],"safe":[231],"deployment":[232],"risks,":[237],"including":[238],"undetected":[239],"incorrect":[240],"interpretations,":[241],"workflows":[245],"safety-critical":[247],"applications.":[248]},"counts_by_year":[],"updated_date":"2026-10-04T09:36:47.201465","created_date":"2026-10-03T00:00:00"}