{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T16:51:54Z","timestamp":1785603114210,"version":"3.56.0"},"reference-count":53,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:00:00Z","timestamp":1705017600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"DOI":"10.3389\/frai.2023.1350306","type":"journal-article","created":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T04:41:05Z","timestamp":1705034465000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":71,"title":["Natural language processing in the era of large language models"],"prefix":"10.3389","volume":"6","author":[{"given":"Arkaitz","family":"Zubiaga","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,1,12]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"2","DOI":"10.7759\/cureus.35179","article-title":"Artificial hallucinations in chatgpt: implications in scientific writing","volume":"15","author":"Alkaissi","year":"2023","journal-title":"Cureus"},{"key":"B2","first-page":"38176","article-title":"Fine-tuning language models to find agreement among humans with diverse preferences","volume":"35","author":"Bakker","year":"2022","journal-title":"Adv. Neural Inform. Proc. Syst"},{"key":"B3","first-page":"381","article-title":"\u201cA systematic review of reproducibility research in natural language processing,\u201d","volume-title":"Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume","author":"Belz","year":"2021"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2311.16989","article-title":"Chatgpt's one-year anniversary: are open-source large language models catching up?","author":"Chen","year":"2023","journal-title":"arXiv"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2307.03109","article-title":"A survey on evaluation of large language models","author":"Chang","year":"2023","journal-title":"arXiv"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-01487-w","article-title":"Dynamics of online hate and misinformation","author":"Cinelli","year":"2021","journal-title":"Scient.Rep"},{"key":"B7","first-page":"1","article-title":"\u201cChatting and cheating: Ensuring academic integrity in the era of chatgpt,\u201d","volume-title":"Innovations in Education and Teaching International","author":"Cotton","year":"2023"},{"key":"B8","first-page":"447","article-title":"\u201cA survey of the state of explainable ai for natural language processing,\u201d","volume-title":"Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing","author":"Danilevsky","year":"2020"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2311.09783","article-title":"Investigating data contamination in modern benchmarks for large language models","author":"Deng","year":"2023","journal-title":"arXiv"},{"key":"B10","article-title":"\u201cPheme: computing veracity: the fourth challenge of big social data,\u201d","volume-title":"Proceedings of ESWC EU Project Networking","author":"Derczynski","year":"2014"},{"key":"B11","first-page":"4171","article-title":"\u201cBert: Pre-training of deep bidirectional transformers for language understanding,\u201d","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Devlin","year":"2019"},{"key":"B12","first-page":"32","article-title":"\u201cUnified language model pre-training for natural language understanding and generation,\u201d","volume-title":"Advances in Neural Information Processing Systems","author":"Dong","year":"2019"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2309.00770","article-title":"Bias and fairness in large language models: a survey","author":"Gallegos","year":"2023","journal-title":"arXiv"},{"key":"B14","first-page":"154","article-title":"Chatgpt and the future of work: a comprehensive analysis of ai's impact on jobs and employment","volume":"1","author":"George","year":"2023","journal-title":"Partners Universal Int. Innovat. J"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2308.08493","article-title":"Time travel in llms: tracing data contamination in large language models","author":"Golchin","year":"2023","journal-title":"arXiv"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2202.06862","article-title":"Threats to pre-trained language models: Survey and taxonomy","author":"Guo","year":"2022","journal-title":"arXiv"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2023.1225093","article-title":"Rationalization for explainable nlp: a survey","author":"Gurrapu","year":"2023","journal-title":"Front. Artif. Intellig"},{"key":"B18","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1145\/3582269.3615599","article-title":"\u201cGender bias and stereotypes in large language models,\u201d","volume-title":"Proceedings of The ACM Collective Intelligence Conference","author":"Kotek","year":"2023"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2308.12032","article-title":"From quantity to quality: boosting llm performance with self-guided data selection for instruction tuning","author":"Li","year":"","journal-title":"arXiv"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2308.10149","article-title":"A survey on fairness in large language models","author":"Li","year":"","journal-title":"arXiv"},{"key":"B21","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Adv. Neural Inform. Proc.Syst"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1907.11692","article-title":"Roberta: a robustly optimized bert pretraining approach","author":"Liu","year":"2019","journal-title":"arXiv"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3560815","article-title":"Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu","year":"2023","journal-title":"ACM Comput. Surv"},{"key":"B24","doi-asserted-by":"crossref","first-page":"157","DOI":"10.18653\/v1\/2022.acl-short.18","article-title":"\u201cData contamination: From memorization to exploitation,\u201d","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","author":"Magar","year":"2022"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.3390\/app12178805","article-title":"From word embeddings to pre-trained language models: a state-of-the-art walkthrough","author":"Mars","year":"2022","journal-title":"Appl. Sci"},{"key":"B26","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.acl-main.173","article-title":"\u201cOn faithfulness and factuality in abstractive summarization,\u201d","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Maynez","year":"2020"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1301.3781","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013","journal-title":"arXiv"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3605943","article-title":"Recent advances in natural language processing via large pre-trained language models: a survey","volume":"56","author":"Min","year":"2023","journal-title":"ACM Computing Surveys"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2215907120","article-title":"The debate over understanding in ais large language models","author":"Mitchell","year":"2023","journal-title":"Proc. National Acad. Sci"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3597307","article-title":"Biases in large language models: origins, inventory and discussion","volume":"15","author":"Navigli","year":"2023","journal-title":"ACM J. Data Inform. Qual"},{"key":"B31","volume-title":"Experimental Evidence on the Productivity Effects of Generative Artificial Intelligence","author":"Noy","year":"2023"},{"key":"B32","doi-asserted-by":"crossref","DOI":"10.1109\/SP40000.2020.00095","article-title":"\u201cPrivacy risks of general-purpose language models,\u201d","volume-title":"2020 IEEE Symposium on Security and Privacy (SP)","author":"Pan","year":"2020"},{"key":"B33","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.3115\/v1\/D14-1162","article-title":"\u201cGlove: Global vectors for word representation,\u201d","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Pennington","year":"2014"},{"key":"B34","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":"J. Mach. Learn. Res"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.155","article-title":"The troubling emergence of hallucination in large language models-an extensive definition, quantification, and prescriptive remediations","author":"Rawte","year":"2023","journal-title":"arXiv"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3624010","article-title":"A survey of privacy attacks in machine learning","volume":"56","author":"Rigaki","year":"2023","journal-title":"ACM Comp. Surv"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1270","DOI":"10.1109\/5.880083","article-title":"Two decades of statistical language modeling: where do we go from here?","volume":"88","author":"Rosenfeld","year":"2000","journal-title":"Proc. IEEE"},{"key":"B38","first-page":"27","article-title":"\u201cAutomatic generation of programming exercises and code explanations using large language models,\u201d","volume-title":"Proceedings of the 2022 ACM Conference on International Computing Education Research","author":"Sarsa","year":"2022"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2211.05100","article-title":"Bloom: A 176b-parameter open-access multilingual language model","author":"Scao","year":"2023","journal-title":"arXiv"},{"key":"B40","first-page":"255","article-title":"\u201cExploiting cloze-questions for few-shot text classification and natural language inference,\u201d","author":"Schick","year":"2021","journal-title":"Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2310.16789","article-title":"Detecting pretraining data from large language models","author":"Shi","year":"2023","journal-title":"arXiv"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2310.10844","article-title":"Survey of vulnerabilities in large language models revealed by adversarial attacks","author":"Shayegani","year":"2023","journal-title":"arXiv"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2310.00892","article-title":"No offense taken: eliciting offensiveness from language models","author":"Srivastava","year":"2023","journal-title":"arXiv"},{"key":"B44","unstructured":"TaoriR.\n            GulrajaniI.\n            ZhangT.\n            DuboisY.\n            LiX.\n            GuestrinC.\n          Stanford Alpaca: An Instruction-Following Llama Model2023"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.13971","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv"},{"key":"B46","first-page":"30","article-title":"\u201cAttention is all you need,\u201d","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.243","article-title":"\u201c kelly is a warm person, joseph is a role model\u201d: Gender biases in llm-generated reference letters","author":"Wan","year":"2023","journal-title":"arXiv"},{"key":"B48","first-page":"214","article-title":"\u201cTaxonomy of risks posed by language models,\u201d","volume-title":"Proceedings of the","author":"Weidinger","year":"2022"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2112.04359","article-title":"Ethical and social risks of harm from language models","author":"Weidinger","year":"2021","journal-title":"arXiv"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2310.06830","article-title":"Lemur: Harmonizing natural language and code for language agents","author":"Xu","year":"2023","journal-title":"arXiv"},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.598","article-title":"Towards generalisable hate speech detection: a review on obstacles and solutions","author":"Yin","year":"2021","journal-title":"PeerJ Comp. Sci"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2309.01219","article-title":"Siren's song in the ai ocean: a survey on hallucination in large language models","author":"Zhang","year":"2023","journal-title":"arXiv"},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.1145\/3639372","article-title":"Explainability for large language models: a survey","author":"Zhao","year":"2023","journal-title":"arXiv"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1350306\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T04:41:32Z","timestamp":1705034492000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1350306\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,12]]},"references-count":53,"alternative-id":["10.3389\/frai.2023.1350306"],"URL":"https:\/\/doi.org\/10.3389\/frai.2023.1350306","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,12]]},"article-number":"1350306"}}