{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T20:48:56Z","timestamp":1769719736759,"version":"3.49.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"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":[[2025,11,16]]},"DOI":"10.1109\/ase63991.2025.00380","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:38Z","timestamp":1769633678000},"page":"4082-4085","source":"Crossref","is-referenced-by-count":0,"title":["TrustVis: A Multi-Dimensional Trustworthiness Evaluation Framework for Large Language Models"],"prefix":"10.1109","author":[{"given":"Ruoyu","family":"Sun","sequence":"first","affiliation":[{"name":"University of Alberta,Canada"}]},{"given":"Da","family":"Song","sequence":"additional","affiliation":[{"name":"Mila - Quebec Artificial Intelligence Institute"}]},{"given":"Jiayang","family":"Song","sequence":"additional","affiliation":[{"name":"Macau University of Science and Technology,China"}]},{"given":"Yuheng","family":"Huang","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}]},{"given":"Lei","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Tokyo,Japan"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A survey on large language models for critical societal domains: Finance, healthcare, and law","author":"Chen","year":"2024"},{"key":"ref2","first-page":"896","article-title":"Do-not-answer: Evaluating safeguards in llms","author":"Wang","year":"2024","journal-title":"Findings of the Association for Computational Linguistics: EACL 2024"},{"key":"ref3","article-title":"Autodan: Generating stealthy jailbreak prompts on aligned large language models","author":"Liu","year":"2024"},{"key":"ref4","article-title":"Introducing v0. 5 of the ai safety benchmark from mlcommons","author":"Vidgen","year":"2024"},{"key":"ref5","article-title":"Universal and transferable adversarial attacks on aligned language models","author":"Zou","year":"2023"},{"key":"ref6","first-page":"rs","article-title":"Assessing the accuracy and reliability of ai-generated medical responses: an evaluation of the chat-gpt model","author":"Johnson","year":"2023","journal-title":"Research square"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.ijcnlp-main.45"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2024.3411928"},{"key":"ref9","article-title":"Giskard: Testing platform for ai models","author":"Giskard"},{"key":"ref10","article-title":"Alert: A comprehensive benchmark for assessing large language models\u2019 safety through red teaming","author":"Tedeschi","year":"2024"},{"key":"ref11","article-title":"Llama guard: Llm-based input-output safeguard for human-ai conversations","author":"Inan","year":"2023"},{"key":"ref12","article-title":"Meta llama guard 2","year":"2024"},{"key":"ref13","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/41.538609"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30217-9_24"},{"key":"ref16","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref17","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"ref18","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref19","article-title":"Trustllm: Trustworthiness in large language models","author":"Sun","year":"2024"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.emnlp-demo.42","article-title":"Walledeval: A comprehensive safety evaluation toolkit for large language models","author":"Gupta","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581268"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.230"}],"event":{"name":"2025 40th IEEE\/ACM International Conference on Automated Software Engineering (ASE)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2025,11,16]]},"end":{"date-parts":[[2025,11,20]]}},"container-title":["2025 40th IEEE\/ACM International Conference on Automated Software Engineering (ASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11334056\/11334198\/11334355.pdf?arnumber=11334355","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T10:07:54Z","timestamp":1769681274000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11334355\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,16]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/ase63991.2025.00380","relation":{},"subject":[],"published":{"date-parts":[[2025,11,16]]}}}