{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:51:35Z","timestamp":1772934695764,"version":"3.50.1"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2312862"],"award-info":[{"award-number":["2312862"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["ROIAG091762"],"award-info":[{"award-number":["ROIAG091762"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11402087","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"3335-3344","source":"Crossref","is-referenced-by-count":0,"title":["Accelerating Causal Network Discovery of Alzheimer's Disease Biomarkers via Scientific Literature-Based Retrieval Augmented Generation"],"prefix":"10.1109","author":[{"given":"Xiaofan","family":"Zhou","sequence":"first","affiliation":[{"name":"University of Illinois Chicago,Computer Science,Chicago,IL,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liangjie","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Illinois Chicago,Computer Science,Chicago,IL,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pinyang","family":"Chen","sequence":"additional","affiliation":[{"name":"Pennsylvania State University,Mathematics,State College,PA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenpeng","family":"Yin","sequence":"additional","affiliation":[{"name":"Pennsylvania State University,Computer Science,State College,PA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Pennsylvania State University,Computer Science,State College,PA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenrui","family":"Hao","sequence":"additional","affiliation":[{"name":"Pennsylvania State University,Mathematics,State College,PA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Cheng","sequence":"additional","affiliation":[{"name":"University of Illinois Chicago,Computer Science,Chicago,IL,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Llama 3 model card","year":"2024"},{"key":"ref2","article-title":"Sparks of artificial general intelligence: Early experiments with gpt-4","author":"Bubeck","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Chemist-x: large language model-empowered agent for reaction condition recommendation in chemical synthesis","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-56989-2"},{"key":"ref5","first-page":"241","article-title":"Statistically efficient greedy equivalence search","volume-title":"Conference on Uncertainty in Artificial Intelligence","author":"Chickering","year":"2020"},{"key":"ref6","article-title":"Lmpriors: Pre-trained language models as task-specific priors","author":"Choi","year":"2022","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.743"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.398"},{"key":"ref9","article-title":"Retrieval-augmented generation for large language models: A survey","author":"Gao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.366"},{"key":"ref11","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.693"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1186\/s12918-016-0348-2"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.287"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae238"},{"key":"ref16","author":"Jiang","year":"2023","journal-title":"Mistral 7b"},{"key":"ref17","author":"Jiang","year":"2024","journal-title":"Mixtral of experts"},{"key":"ref18","article-title":"Can large language models infer causation from correlation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Jin","year":"2024"},{"key":"ref19","article-title":"Efficient causal graph discovery using large language models","author":"Jiralerspong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Addressing uncertainty in llms to enhance reliability in generative ai","author":"Kaur","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Generalization through memorization: Nearest neighbor language models","author":"Khandelwal","year":"2019","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Causal reasoning and large language models: Opening a new frontier for causality","author":"Kiciman","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref23","article-title":"Alzheimerrag: Multimodal retrieval augmented generation for pubmed articles","author":"Lahiri","year":"2024","journal-title":"ar Xiv preprint arXiv:2412.16701"},{"key":"ref24","article-title":"Retrieval-augmented generation to improve math question-answering: Trade-offs between groundedness and human preference","author":"Levonian","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.281"},{"key":"ref27","article-title":"Can large language models build causal graphs","volume-title":"Proceedings of the Causal Machine Learning for Real-World Impact (CML4Impact) Workshop at NeurIPS 2022","author":"Long","year":"2022"},{"key":"ref28","article-title":"Can large language models build causal graphs","author":"Long","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06735-9"},{"key":"ref30","article-title":"Superpo-sition prompting: Improving and accelerating retrieval-augmented generation","volume-title":"Forty-first International Conference on Machine Learning","author":"Merth","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1017\/s0266466603004109"},{"key":"ref32","first-page":"3956","article-title":"Analyzing uncertainty in neural machine translation","volume-title":"International Conference on Machine Learning","author":"Ott","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/6216530"},{"issue":"140","key":"ref34","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06924-6"},{"key":"ref36","article-title":"Raptor: Recursive abstractive processing for tree-organized retrieval","volume-title":"The Twelfth International Conference on Learning Representations","author":"Sarthi","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.635"},{"key":"ref38","first-page":"16857","article-title":"Mpnet: Masked and permuted pre-training for language under-standing","volume":"33","author":"Song","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1177\/089443939100900106"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s41060-017-0094-6"},{"key":"ref41","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref42","article-title":"Biorag: A rag-11m frame-work for biological question reasoning","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3389\/fncel.2023.1279046"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.691"},{"key":"ref45","article-title":"Retrieval-based controllable molecule generation","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.184"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1381"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2023.1268566"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1038\/s44401-024-00004-1"},{"key":"ref51","article-title":"Causal graph discovery with retrieval-augmented gen-eration based large language models","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00632-7"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11402087.pdf?arnumber=11402087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T07:14:55Z","timestamp":1772867695000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11402087\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11402087","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}