{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T21:19:10Z","timestamp":1773263950948,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["U01AG068057"],"award-info":[{"award-number":["U01AG068057"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,12]]},"DOI":"10.1109\/icdmw69685.2025.00239","type":"proceedings-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:50:39Z","timestamp":1773172239000},"page":"1985-1989","source":"Crossref","is-referenced-by-count":0,"title":["Who Matters More in Radiology Report Generation: Vision Encoders or Language Models?"],"prefix":"10.1109","author":[{"given":"Kun","family":"Zhao","sequence":"first","affiliation":[{"name":"University of Pittsburgh,Department of Electrical & Computer Engineering,Pittsburgh,PA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Du","sequence":"additional","affiliation":[{"name":"University of Pittsburgh,Department of Electrical & Computer Engineering,Pittsburgh,PA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rhianna","family":"Zhang","sequence":"additional","affiliation":[{"name":"Council Rock High School North,Newtown,PA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Zhan","sequence":"additional","affiliation":[{"name":"University of Pittsburgh,Department of Electrical & Computer Engineering,Pittsburgh,PA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongkuan","family":"Xu","sequence":"additional","affiliation":[{"name":"NC State University,Department of Computer Science,Raleigh,NC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengfei","family":"Gu","sequence":"additional","affiliation":[{"name":"University of Texas Rio Grande Valley,Department of Computer Science,Edinburg,TX,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoteng","family":"Tang","sequence":"additional","affiliation":[{"name":"University of Texas Rio Grande Valley,Department of Computer Science,Edinburg,TX,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Soullmate: An adaptive 11 m -driven system for advanced mental health support and assessment, based on a systematic application survey","volume-title":"arXiv preprint","author":"Guo","year":"2024"},{"key":"ref2","article-title":"X-ray made simple: Lay radiology report generation and robust evaluation","volume-title":"arXiv preprint","author":"Zhao","year":"2024"},{"key":"ref3","article-title":"Soullmate: An application enhancing diverse mental health support with adaptive 11 ms, prompt engineering, and rag techniques","volume-title":"arXiv preprint","author":"Guo","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.bionlp-1.31"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.4798864","article-title":"Constrained multiview representation for self-supervised contrastive learning","volume-title":"arXiv preprint","author":"Dai","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2025.02.024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43898-1_14"},{"key":"ref8","article-title":"Llavanext: Improved reasoning, ocr, and world knowledge","volume-title":"arXiv preprint","author":"Liu","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.33"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CBMS65348.2025.00043"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-025-02742-6"},{"key":"ref12","article-title":"X-ray made simple: Lay radiology report generation and robust evaluation","volume-title":"arXiv preprint","author":"Zhao","year":"2025"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaaiss.v5i1.35550"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CBMS65348.2025.00059"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.911"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.5351694","article-title":"Dre: An effective dual-refined method for integrating small and large language models in open-domain dialogue evaluation","volume-title":"arXiv preprint","author":"Zhao","year":"2025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref20","article-title":"Dinov2: Learning robust visual features without supervision","volume-title":"arXiv preprint","author":"Oquab","year":"2023"},{"key":"ref21","first-page":"353","article-title":"Med-flamingo: a multimodal medical few-shot learner","volume-title":"Machine Learning for Health (MLAH)","author":"Moor","year":"2023"},{"key":"ref22","article-title":"Openflamingo: An open-source framework for training large autoregressive vision-language models","volume-title":"arXiv preprint","author":"Awadalla","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1056\/aioa2300138"},{"key":"ref24","article-title":"Palm-e: An embodied multimodal language model","volume-title":"arXiv preprint","author":"Driess","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1240"},{"key":"ref26","article-title":"Elixr: Towards a general purpose x-ray artificial intelligence system through alignment of large language models and radiology vision encoders","volume-title":"arXiv preprint","author":"Xu","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.212482"},{"key":"ref28","article-title":"Palm 2 technical report","volume-title":"arXiv preprint","author":"Anil","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2025.100153"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1161\/01.CTR.101.23.e215"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.bionlp-1.35"},{"key":"ref33","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref35","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization","author":"Banerjee","year":"2005"},{"key":"ref36","article-title":"Bertscore: Evaluating text generation with bert","volume-title":"arXiv preprint","author":"Zhang","year":"2019"},{"key":"ref37","article-title":"Chexbert: combining automatic labelers and expert annotations for accurate radiology report labeling using bert","volume-title":"arXiv preprint","author":"Smit","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2023.100802"},{"key":"ref39","article-title":"Radgraph: Extracting clinical entities and relations from radiology reports","volume-title":"arXiv preprint","author":"Jain","year":"2021"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.findings-emnlp.21","article-title":"Green: Generative radiology report evaluation and error notation","volume-title":"arXiv preprint","author":"Ostmeier","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3437359.3465593"}],"event":{"name":"2025 IEEE International Conference on Data Mining Workshops (ICDMW)","location":"Washington, DC, USA","start":{"date-parts":[[2025,11,12]]},"end":{"date-parts":[[2025,11,15]]}},"container-title":["2025 IEEE International Conference on Data Mining Workshops (ICDMW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11415623\/11415713\/11416054.pdf?arnumber=11416054","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T05:19:02Z","timestamp":1773206342000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11416054\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,12]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icdmw69685.2025.00239","relation":{},"subject":[],"published":{"date-parts":[[2025,11,12]]}}}