{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T02:02:02Z","timestamp":1789178522376,"version":"build-2803163510"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,31]]},"DOI":"10.1109\/icstw64639.2025.10962467","type":"proceedings-article","created":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T17:47:42Z","timestamp":1744825662000},"page":"375-382","source":"Crossref","is-referenced-by-count":7,"title":["Adaptive Testing for LLM-Based Applications: A Diversity-Based Approach"],"prefix":"10.1109","author":[{"given":"Juyeon","family":"Yoon","sequence":"first","affiliation":[{"name":"KAIST,School of Computing,Daejeon,Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Feldt","sequence":"additional","affiliation":[{"name":"Chalmers University,Dept. of Computer Science &amp; Engineering,Gothenburg,Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shin","family":"Yoo","sequence":"additional","affiliation":[{"name":"KAIST,School of Computing,Daejeon,Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Google ai overview","year":"2024"},{"key":"ref2","article-title":"Perplexity ai search engine","year":"2024"},{"key":"ref3","article-title":"Duolingo max with gpt-4","year":"2024"},{"key":"ref4","article-title":"Larp: Language-agent role play for open-world games","author":"Yan","year":"2023"},{"key":"ref5","article-title":"Gptrpg","year":"2024"},{"key":"ref6","article-title":"Ai dungeon","year":"2024"},{"key":"ref7","article-title":"Github copilot","year":"2024"},{"key":"ref8","article-title":"An empirical study on challenges for llm developers","author":"Chen","year":"2024"},{"key":"ref9","article-title":"Demystifying Issues, Causes and Solutions in LLM Open-Source Projects","author":"Cai","year":"2024"},{"key":"ref10","article-title":"Langchain prompt template","year":"2024"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.14778\/3685800.3685835","article-title":"SPADE: Synthesizing Data Quality Assertions for Large Language Model Pipelines","author":"Shankar","year":"2024"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1145\/3654777.3676450","article-title":"Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences","author":"Shankar","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30502-6_23"},{"key":"ref14","article-title":"Adaptive Test Generation with Qgrams","author":"Biagiola","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2005.844059"},{"key":"ref16","article-title":"A Software Engineering Perspective on Testing Large Language Models: Research, Practice, Tools and Benchmarks","author":"Hudson","year":"2024"},{"key":"ref17","article-title":"Deepeval dataset generation","year":"2024"},{"key":"ref18","article-title":"Promptfoo dataset generation","year":"2024"},{"key":"ref19","article-title":"Promptfoo","year":"2024"},{"key":"ref20","article-title":"Trulens","year":"2024"},{"key":"ref21","article-title":"Langsmith","year":"2024"},{"key":"ref22","article-title":"Giskard","year":"2024"},{"key":"ref23","article-title":"Deepeval","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30502-6_23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2001420.2001452"},{"key":"ref27","first-page":"223","article-title":"Test Set Diameter: Quantifying the Diversity of Sets of Test Cases","volume-title":"2016 IEEE International Conference on Software Testing, Verification and Validation (ICST)","author":"Feldt"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2884781.2884791"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE.2003.1251065"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2009.02.022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.824"},{"key":"ref32","article-title":"Multitask prompted training enables zero-shot task generalization","author":"Sanh","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2006.92"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2012.6227083"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"}],"event":{"name":"2025 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW)","location":"Naples, Italy","start":{"date-parts":[[2025,3,31]]},"end":{"date-parts":[[2025,4,4]]}},"container-title":["2025 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10962452\/10962453\/10962467.pdf?arnumber=10962467","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T05:58:45Z","timestamp":1744869525000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10962467\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,31]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icstw64639.2025.10962467","relation":{},"subject":[],"published":{"date-parts":[[2025,3,31]]}}}