{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T05:07:44Z","timestamp":1737176864388,"version":"3.33.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"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":[[2024,12,15]]},"DOI":"10.1109\/bigdata62323.2024.10825505","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"8301-8308","source":"Crossref","is-referenced-by-count":0,"title":["On Text Granularity and Metric Frameworks for Large Language Model Content Detection"],"prefix":"10.1109","author":[{"given":"Linh","family":"Le","sequence":"first","affiliation":[{"name":"Kennesaw State University,College of Computing and Software Engineering,Kennesaw,Georgia,USA"}]},{"given":"Dung","family":"Tran","sequence":"additional","affiliation":[{"name":"Harvard Medical School,Brigham and Women’s Hospital,Boston,Massachusetts,USA"}]}],"member":"263","reference":[{"article-title":"A survey of large language models","year":"2023","author":"Zhao","key":"ref1"},{"article-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref2"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"article-title":"Palm: Scaling language modeling with pathways","year":"2022","author":"Chowdhery","key":"ref4"},{"year":"2023","key":"ref5","article-title":"Gpt-4"},{"year":"2022","key":"ref6","article-title":"Introducing chatgpt"},{"article-title":"Detectgpt: Zero-shot machine-generated text detection using probability curvature","year":"2023","author":"Mitchell","key":"ref7"},{"article-title":"A watermark for large language models","year":"2023","author":"Kirchenbauer","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2008.11-07-647"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w17-4413"},{"year":"2024","key":"ref15","article-title":"Meta llama 3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1093\/oed\/1047657781"},{"article-title":"Real or fake? learning to discriminate machine from human generated text","year":"2019","author":"Bakhtin","key":"ref17"},{"article-title":"Release strategies and the social impacts of language models","year":"2019","author":"Solaiman","key":"ref18"},{"article-title":"Automatic detection of generated text is easiest when humans are fooled","year":"2019","author":"Ippolito","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0251415"},{"article-title":"Synthetic text detection: Systemic literature review","year":"2022","author":"Guerrero","key":"ref21"},{"article-title":"Roberta: A robustly optimized bert pretraining approach","year":"2019","author":"Liu","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3606274.3606279"},{"article-title":"Dna-gpt: Divergent n-gram analysis for training-free detection of gptgenerated text","year":"2023","author":"Yang","key":"ref24"},{"article-title":"Raidar: generative ai detection via rewriting","year":"2024","author":"Mao","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.bea-1.58"},{"key":"ref27","article-title":"Gpt paternity test: Gpt generated text detection with gpt genetic inheritance","author":"Yu","year":"2023","journal-title":"CoRR"},{"article-title":"Neural text generation with unlikelihood training","year":"2019","author":"Welleck","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.448"},{"article-title":"Generating sequences with recurrent neural networks","year":"2013","author":"Graves","key":"ref30"},{"key":"ref31","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"Sutskever","year":"2014","journal-title":"Advances in neural information processing systems"},{"article-title":"Sequence-to-sequence learning as beamsearch optimization","year":"2016","author":"Wiseman","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1082"},{"article-title":"The curious case of neural text degeneration","year":"2019","author":"Holtzman","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001493000339"},{"key":"ref36","first-page":"16857","article-title":"Mpnet: Masked and permuted pre-training for language understanding","volume":"33","author":"Song","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D19-1410","article-title":"Sentence-bert: Sentence embeddings using siamese bert-networks","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing","author":"Reimers"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2649-2"},{"year":"2020","key":"ref40","article-title":"pandas-dev\/pandas: Pandas"},{"article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","year":"2015","author":"Abadi","key":"ref41"},{"key":"ref42","first-page":"38","article-title":"Transformers: State-ofthe-art natural language processing","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","author":"Wolf"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2007.55"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03021"},{"article-title":"Parrot: Paraphrase generation for nlu","year":"2021","author":"Damodaran","key":"ref45"},{"issue":"1","key":"ref46","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"year":"2024","key":"ref47","article-title":"Llama 3 8b instruct"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","start":{"date-parts":[[2024,12,15]]},"location":"Washington, DC, USA","end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10824975\/10824942\/10825505.pdf?arnumber=10825505","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:18:48Z","timestamp":1737101928000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10825505\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10825505","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}