{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T22:19:03Z","timestamp":1726265943239},"reference-count":40,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T00:00:00Z","timestamp":1741305600000},"content-version":"vor","delay-in-days":347,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["IIS-2310260, IIS-1849085, IIS-2224843"],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Commun. ACM"],"published-print":{"date-parts":[[2024,4]]},"abstract":"While many detection methods have been proposed, understanding the challenges is far more daunting.<\/jats:p>","DOI":"10.1145\/3624725","type":"journal-article","created":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T18:26:33Z","timestamp":1709835993000},"page":"50-59","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["The Science of Detecting LLM-Generated Text"],"prefix":"10.1145","volume":"67","author":[{"given":"Ruixiang","family":"Tang","sequence":"first","affiliation":[{"name":"Rice University, Houston, TX, USA"}]},{"given":"Yu-Neng","family":"Chuang","sequence":"additional","affiliation":[{"name":"Rice University, Houston, TX, USA"}]},{"given":"Xia","family":"Hu","sequence":"additional","affiliation":[{"name":"Rice University, Houston, TX, USA"}]}],"member":"320","published-online":{"date-parts":[[2024,3,25]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Proceedings of the 2021 IEEE Symp. Security and Privacy. IEEE, 121--140","author":"Abdelnabi S.","unstructured":"Abdelnabi, S. and Fritz, M. Adversarial watermarking transformer: Towards tracing text provenance with data hiding. In Proceedings of the 2021 IEEE Symp. Security and Privacy. IEEE, 121--140."},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45496-9_14"},{"key":"e_1_2_1_3_1","first-page":"3247","article-title":"Detecting bot-generated text by characterizing linguistic accommodation in human-bot interactions. Findings of the Association for Computational Linguistics. ACL, Bangkok","volume":"3235","author":"Bhatt P.","year":"2021","unstructured":"Bhatt, P. and Rios, A. Detecting bot-generated text by characterizing linguistic accommodation in human-bot interactions. Findings of the Association for Computational Linguistics. ACL, Bangkok, Thailand, 2021, 3235--3247.","journal-title":"Thailand"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/49.464718"},{"key":"e_1_2_1_5_1","first-page":"1","article-title":"An estimate of an upper bound for the entropy of english","volume":"18","author":"Brown P.F.","year":"1992","unstructured":"Brown, P.F. et al. An estimate of an upper bound for the entropy of english. Computational Linguistics 18, 1 (1992), 31--40.","journal-title":"Computational Linguistics"},{"key":"e_1_2_1_6_1","volume-title":"Proceedings of the 59th Annual Meeting of the ACL and the 11th Intern. Joint Conf. on NLP. ACL","author":"Clark E.","year":"2021","unstructured":"Clark, E. et al. All that's 'human' is not gold: Evaluating human evaluation of generated text. In Proceedings of the 59th Annual Meeting of the ACL and the 11th Intern. Joint Conf. on NLP. ACL, Bangkok, Thailand, 2021, 7282--7296."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892269"},{"key":"e_1_2_1_8_1","first-page":"196","article-title":"A tool for evaluating human detection of machine-generated text. In Proceedings of the 2020 Conf","volume":"189","author":"Dugan L.","year":"2020","unstructured":"Dugan, L., Ippolito, D., Kirubarajan, A. and Callison-Burch, C. Roft: A tool for evaluating human detection of machine-generated text. In Proceedings of the 2020 Conf. Empirical Methods in NLP: System Demonstrations. ACL Online, 2020, 189--196.","journal-title":"Empirical Methods in NLP: System Demonstrations. ACL Online"},{"key":"e_1_2_1_9_1","volume-title":"Proceedings of the 37th AAAI Conf. on AI. AAAI, Washington, D.C., USA","author":"Dugan L.","year":"2023","unstructured":"Dugan, L. et al. Real or fake text? Investigating human ability to detect boundaries between human-written and machine-generated text. In Proceedings of the 37th AAAI Conf. on AI. AAAI, Washington, D.C., USA, 2023."},{"key":"e_1_2_1_10_1","volume-title":"College Instructor Put on Blast for Accusing Students of Using Chatgpt on Final Assignments","author":"Ede-Osifo U.","year":"2023","unstructured":"Ede-Osifo, U. College Instructor Put on Blast for Accusing Students of Using Chatgpt on Final Assignments, 2023; https:\/\/nbcnews.to\/3G15wg6"},{"key":"e_1_2_1_11_1","volume-title":"Networks","author":"Elsen-Rooney M.","year":"2023","unstructured":"Elsen-Rooney, M. NYC Education Department Blocks Chatgpt on School Devices, Networks, 2023; https:\/\/bit.ly\/47kmnXz"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0251415"},{"key":"e_1_2_1_13_1","volume-title":"Proceedings of the 57th Annual Meeting of the ACL","author":"Fan A.","year":"2019","unstructured":"Fan, A. et al. Eli5: Long form question answering. In Proceedings of the 57th Annual Meeting of the ACL (Florence, Italy, 2019), 3558--3567."},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.443"},{"key":"e_1_2_1_16_1","volume-title":"Unsupervised and Distributional Detection of Machine-Generated Text","author":"Gall\u00e9 M.","year":"2021","unstructured":"Gall\u00e9, M., Rozen, J., Kruszewski, G. and Elsahar, H. Unsupervised and Distributional Detection of Machine-Generated Text, 2021, arXiv:2111.02878."},{"key":"e_1_2_1_17_1","first-page":"116","article-title":"GLTR: Statistical detection and visualization of generated text. In Proceedings of the 57th Annual Meeting of the ACL","volume":"111","author":"Gehrmann S.","year":"2019","unstructured":"Gehrmann, S., Strobelt, H. and Rush, A.M. GLTR: Statistical detection and visualization of generated text. In Proceedings of the 57th Annual Meeting of the ACL: System Demonstrations, 2019, 111--116.","journal-title":"System Demonstrations"},{"key":"e_1_2_1_18_1","volume-title":"et al. How close is chatgpt to human experts? Comparison Corpus, Evaluation, and Detection","author":"Guo B.","year":"2023","unstructured":"Guo, B. et al. How close is chatgpt to human experts? Comparison Corpus, Evaluation, and Detection. 2023, arXiv:2301.07597."},{"key":"e_1_2_1_19_1","first-page":"16","volume":"1","author":"Holtzman A.","year":"2019","unstructured":"Holtzman, A. et al. The Curious Case of Neural Text Degeneration. 2019, 1--16, arXiv:1904.09751.","journal-title":"The Curious Case of Neural Text Degeneration"},{"key":"e_1_2_1_20_1","volume-title":"Proceedings of the 58th Annual Meeting of the ACL, 2020, 1808","author":"Ippolito D.","year":"1822","unstructured":"Ippolito, D., Duckworth, D., Callison-Burch, C. and Eck, D. Automatic detection of generated text is easiest when humans are fooled. In Proceedings of the 58th Annual Meeting of the ACL, 2020, 1808--1822."},{"key":"e_1_2_1_21_1","volume-title":"Proceedings of IEEE 2009 Intern. Conf. Information and Multimedia Technology. IEEE Computer Society, Washington D.C., U.S., 230--234","author":"Jalil Z.","unstructured":"Jalil, Z. and Mirza, A.M. A review of digital watermarking techniques for text documents. In Proceedings of IEEE 2009 Intern. Conf. Information and Multimedia Technology. IEEE Computer Society, Washington D.C., U.S., 230--234."},{"key":"e_1_2_1_22_1","volume-title":"Proceedings of the 8th ACM Workshop on AI and Security. ACM","author":"Kantchelian A.","year":"2015","unstructured":"Kantchelian, A. et al. Better malware ground truth: Techniques for weighting anti-virus vendor labels. In Proceedings of the 8th ACM Workshop on AI and Security. ACM, Denver, CO, USA, 2015, 45--56."},{"key":"e_1_2_1_23_1","volume-title":"et al. A Watermark for Large Language Models","author":"Kirchenbauer J.","year":"2023","unstructured":"Kirchenbauer, J. et al. A Watermark for Large Language Models. 2023, arXiv:2301.10226."},{"key":"e_1_2_1_24_1","first-page":"13","article-title":"Roberta","volume":"1","author":"Liu Y.","year":"2019","unstructured":"Liu, Y. et al. Roberta: A Robustly Optimized BERT Pretraining Approach. 2019, 1--13, arXiv:1907.11692.","journal-title":"A Robustly Optimized BERT Pretraining Approach"},{"key":"e_1_2_1_25_1","volume-title":"Findings of the ACL: EMNLP","author":"Massarelli L.","year":"2020","unstructured":"Massarelli, L. et al. How decoding strategies affect the verifiability of generated text. In Findings of the ACL: EMNLP 2020. ACL Online, 223--235."},{"key":"e_1_2_1_26_1","unstructured":"OpenAI. Gpt-2-Output-Dataset. 2021; https:\/\/github.com\/OpenAI.openai\/gpt-2-output-dataset."},{"key":"e_1_2_1_27_1","volume-title":"Proceedings of the 29th Intern. Conf. Computational Linguistics.(Gyeongju, Republic of Korea","author":"Pagnoni A.","year":"2022","unstructured":"Pagnoni, A., Graciarena, M. and Tsvetkov, Y. Threat scenarios and best practices to detect neural fake news. In Proceedings of the 29th Intern. Conf. Computational Linguistics.(Gyeongju, Republic of Korea, 2022), 1233--1249."},{"key":"e_1_2_1_28_1","volume-title":"Proceedings of the 29th Intern. Conf. Computational Linguistics.","author":"Pagnoni A.","year":"2022","unstructured":"Pagnoni, A., Graciarena, M. and Tsvetkov, Y. Threat scenarios and best practices to detect neural fake news. In Proceedings of the 29th Intern. Conf. Computational Linguistics. 2022, 1233--1249."},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.3758\/s13423-014-0585-6"},{"key":"e_1_2_1_30_1","volume-title":"Proceedings of the 2022 Conf. North American Chapter of the ACL: Human Language Technologies. (ACL Seattle, WA, U.S.","author":"Rodriguez J.","year":"2022","unstructured":"Rodriguez, J. et al. Cross-domain detection of GPT-2-generated technical text. In Proceedings of the 2022 Conf. North American Chapter of the ACL: Human Language Technologies. (ACL Seattle, WA, U.S., 2022), 1213--1233."},{"key":"e_1_2_1_31_1","volume-title":"Chatgpt Passes MBA Exam given by a Wharton Professor","author":"Rosenblatt K.","year":"2023","unstructured":"Rosenblatt, K. Chatgpt Passes MBA Exam given by a Wharton Professor, 2023; https:\/\/bit.ly\/3G9824b"},{"key":"e_1_2_1_32_1","volume-title":"et al. Can AI-generated Text Be Reliably Detected?","author":"Sadasivan V.S.","year":"2023","unstructured":"Sadasivan, V.S. et al. Can AI-generated Text Be Reliably Detected? 2023, arXiv:2303.11156."},{"key":"e_1_2_1_33_1","first-page":"1","author":"Shakeel D.","year":"2021","unstructured":"Shakeel, D. and Jain, N. Fake News Detection and Fact Verification Using Knowledge Graphs and Machine Learning. Feb. 2021, 1--7.","journal-title":"Fake News Detection and Fact Verification Using Knowledge Graphs and Machine Learning."},{"key":"e_1_2_1_34_1","first-page":"46","volume":"1","author":"Solaiman I.","year":"2019","unstructured":"Solaiman, I. et al. Release Strategies and the Social Impacts of Language Models. 2019, 1--46, arXiv:1908.09203.","journal-title":"Release Strategies and the Social Impacts of Language Models"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1162\/089120103321337458"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/1161366.1161397"},{"key":"e_1_2_1_37_1","first-page":"2016","article-title":"TURINGBENCH: A benchmark environment for turing test in the age of neural text generation","volume":"2001","author":"Uchendu A.","year":"2021","unstructured":"Uchendu, A. et al. TURINGBENCH: A benchmark environment for turing test in the age of neural text generation. In Findings of the ACL EMNLP, 2021, 2001--2016.","journal-title":"Findings of the ACL EMNLP"},{"key":"e_1_2_1_38_1","unstructured":"Vincent J. Meta's Powerful AI Language Model Has Leaked Online---What Happens Now? 2023; https:\/\/bit.ly\/49I0gf7"},{"key":"e_1_2_1_39_1","first-page":"9054","article-title":"Defending against neural fake news","volume":"32","author":"Zellers R.","year":"2019","unstructured":"Zellers, R. et al. Defending against neural fake news. Advances in Neural Information Processing Systems 32 (2019), 9054--9065.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_40_1","volume-title":"Proceedings of the 2020 Conf. Empirical Methods in NLP. ACL","author":"Zhong W.","year":"2020","unstructured":"Zhong, W. et al. Neural deepfake detection with factual structure of text. In Proceedings of the 2020 Conf. Empirical Methods in NLP. ACL, Minneapolis, MN, 2020, 2461--2470."}],"container-title":["Communications of the ACM"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3624725","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3624725","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T22:48:51Z","timestamp":1711493331000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624725"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,25]]},"references-count":40,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["10.1145\/3624725"],"URL":"http:\/\/dx.doi.org\/10.1145\/3624725","relation":{},"ISSN":["0001-0782","1557-7317"],"issn-type":[{"value":"0001-0782","type":"print"},{"value":"1557-7317","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,25]]},"assertion":[{"value":"2024-03-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}
