{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T09:20:58Z","timestamp":1768382458007,"version":"3.49.0"},"reference-count":147,"publisher":"World Scientific Pub Co Pte Ltd","funder":[{"DOI":"10.13039\/100000057","name":"National Institute of General Medical Sciences","doi-asserted-by":"publisher","award":["R35-GM126985"],"award-info":[{"award-number":["R35-GM126985"]}],"id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000092","name":"U.S. National Library of Medicine","doi-asserted-by":"publisher","award":["RO1-LM013392"],"award-info":[{"award-number":["RO1-LM013392"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Artif. Intell. Robot. Res."],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>Large language models (LLMs) and prompt-based learning as transformative tools have been widely used across both academic and industrial domains. This paper reviews the current landscape of LLM applications, examining their principles, methodologies, strengths, and limitations. Beginning with an overview of the evolution from traditional feature engineering to prompt-based approaches, it highlights the applications of LLMs in diverse fields, including bioinformatics, materials science, and drug discovery. The review further examines the technical intricacies of prompt-based learning, contrasting hard and soft prompt techniques and their respective contributions to optimizing model performance. Real-world implementations are analyzed, with a focus on applications in bioinformatics and financial technology, alongside a discussion of pressing challenges related to data security and privacy. This paper also investigates the economic value generated by LLMs and their potential societal and workforce impacts, such as industry disruption and new job creation. The anticipated trajectory of LLMs and their broader societal implications are discussed, emphasizing the need for continued research and policy to guide its responsible development.<\/jats:p>","DOI":"10.1142\/s2972335325300019","type":"journal-article","created":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T07:03:33Z","timestamp":1746342213000},"source":"Crossref","is-referenced-by-count":0,"title":["Large Language Models and Prompt-Based Learning: Frontiers and Challenges in Cross-Disciplinary Applications"],"prefix":"10.1142","volume":"02","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3969-2679","authenticated-orcid":false,"given":"Yibo","family":"Chen","sequence":"first","affiliation":[{"name":"Institute for Data Science and Informatics, Bond Life Sciences Center, University of Missouri, Columbia, MO 65211, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5453-6888","authenticated-orcid":false,"given":"Gangqing","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Microbiology, Immunology, and Cell Biology, West Virginia University School of Medicine, Morgantown, WV 26506, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3761-3791","authenticated-orcid":false,"given":"Chun","family":"Xia","sequence":"additional","affiliation":[{"name":"TSVC, Los Altos, CA 94022, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0404-1761","authenticated-orcid":false,"given":"Lihua","family":"Yu","sequence":"additional","affiliation":[{"name":"LifeMine Therapeutics, Cambridge, MA 02140, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6145-8096","authenticated-orcid":false,"given":"Mihail","family":"Popescu","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Biostatistics and Medical Epidemiology, University of Missouri, Columbia, MO 65211, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4809-0514","authenticated-orcid":false,"given":"Dong","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Bond Life Sciences Center, Institute for Data Science and Informatics, University of Missouri, Columbia, MO 65211, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2025,6,17]]},"reference":[{"key":"S2972335325300019BIB001","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"S2972335325300019BIB002","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"issue":"2266","key":"S2972335325300019BIB003","first-page":"20210068","volume":"478","author":"Goyal A.","year":"2022","journal-title":"Proc. R. Soc. A Math. Phys. Eng. Sci."},{"key":"S2972335325300019BIB004","first-page":"1877","volume-title":"Advances in Neural Information Processing Systems","author":"Brown T.","year":"2020"},{"key":"S2972335325300019BIB005","unstructured":"W. X. Zhao\n                      et al.\n                      , A survey of large language models, preprint (2024), arXiv:2303.18223, https:\/\/doi.org\/10.48550\/arXiv.2303.18223."},{"key":"S2972335325300019BIB006","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8"},{"issue":"2018","key":"S2972335325300019BIB007","first-page":"39976","volume":"6","author":"Petrovi\u0107 V. M.","journal-title":"IEEE Access"},{"key":"S2972335325300019BIB008","doi-asserted-by":"crossref","unstructured":"D. R. Heath, Prediction machines: The simple economics of artificial intelligence: by Ajay Agrawal, Joshua Gans and Avi Goldfarb, published in 2018 by Harvard Business Review Press, 272 pp. $30.00 (hardcover), Kindle Edition: $16.19, ISBN:978-1-633695672, J. Inf. Technol. Case Appl. Res.\n                      21\n                      (3\u20134) (2019) 163\u2013166, https:\/\/doi.org\/10.1080\/15228053.2019.1673511.","DOI":"10.1080\/15228053.2019.1673511"},{"key":"S2972335325300019BIB009","doi-asserted-by":"publisher","DOI":"10.1016\/j.techfore.2016.08.019"},{"key":"S2972335325300019BIB010","volume-title":"Statistical Methods for Speech Recognition, Language, Speech, and Communication","author":"Jelinek F.","year":"1997"},{"key":"S2972335325300019BIB011","doi-asserted-by":"publisher","DOI":"10.1145\/1034780.1034781"},{"key":"S2972335325300019BIB012","doi-asserted-by":"publisher","DOI":"10.1109\/5.880083"},{"key":"S2972335325300019BIB013","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2002-303"},{"key":"S2972335325300019BIB014","doi-asserted-by":"publisher","DOI":"10.21236\/ADA440321"},{"key":"S2972335325300019BIB015","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-02130-5_2"},{"key":"S2972335325300019BIB016","doi-asserted-by":"publisher","DOI":"10.3115\/1034678.1034712"},{"key":"S2972335325300019BIB017","doi-asserted-by":"publisher","DOI":"10.1109\/29.32278"},{"key":"S2972335325300019BIB018","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.912312"},{"key":"S2972335325300019BIB019","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"S2972335325300019BIB020","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-720"},{"key":"S2972335325300019BIB021","unstructured":"T. Mikolov, I. Sutskever, K. Chen, G. Corrado and J. Dean, Distributed representations of words and phrases and their compositionality, preprint (2013), arXiv:1310.4546, https:\/\/doi.org\/10.48550\/arXiv.1310.4546."},{"key":"S2972335325300019BIB022","unstructured":"T. Mikolov, K. Chen, G. Corrado and J. Dean, Efficient estimation of word representations in vector space, preprint (2013), arXiv:1301.3781, https:\/\/doi.org\/10.48550\/arXiv.1301.3781."},{"key":"S2972335325300019BIB023","doi-asserted-by":"crossref","unstructured":"M. Peters\n                      et al.\n                      , Deep contextualized word representations, in\n                      Proc. 2018 Conf. North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)\n                      (Association for Computational Linguistics, 2018), pp. 2227\u20132237, https:\/\/doi.org\/10.18653\/v1\/N18-1202.","DOI":"10.18653\/v1\/N18-1202"},{"key":"S2972335325300019BIB024","unstructured":"A. Vaswani\n                      et al.\n                      , Attention is all you need, preprint (2017), arXiv:1706.03762, https:\/\/doi.org\/10.48550\/arXiv.1706.03762."},{"key":"S2972335325300019BIB025","unstructured":"J. Devlin, M.W. Chang, K. Lee and K. Toutanova, BERT: Pre-training of deep bidirectional transformers for language understanding, preprint (2019), arXiv:1810.04805, https:\/\/doi.org\/10.48550\/arXiv.1810.04805."},{"key":"S2972335325300019BIB026","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"S2972335325300019BIB027","unstructured":"W. Fedus, B. Zoph and N. Shazeer, Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity, preprint (2021), arXiv:2101.03961, https:\/\/doi.org\/10.48550\/arXiv.2101.03961."},{"key":"S2972335325300019BIB028","unstructured":"A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, and I. Sutskever, Language models are unsupervised multitask learners, OpenAI Technical Report (2019), https:\/\/cdn.openai.com\/better-language-models\/language_models_are_unsupervised_multitask_learners.pdf."},{"key":"S2972335325300019BIB029","unstructured":"Y. Liu\n                      et al.\n                      , RoBERTa: A robustly optimized BERT pretraining approach, preprint (2019), arXiv:1907.11692, https:\/\/doi.org\/10.48550\/arXiv.1907.11692."},{"key":"S2972335325300019BIB030","unstructured":"V. Sanh\n                      et al.\n                      , Multitask prompted training enables zero-shot task generalization, preprint (2021), arXiv:2110.08207, https:\/\/doi.org\/10.48550\/arXiv.2110.08207."},{"key":"S2972335325300019BIB031","unstructured":"T. Wang\n                      et al.\n                      , What language model architecture and pretraining objective work best for zero-shot generalization? preprint (2022), arXiv:2204.05832, https:\/\/doi.org\/10.48550\/arXiv.2204.05832."},{"key":"S2972335325300019BIB032","unstructured":"M. Shanahan, Talking about large language models, preprint (2023), arXiv:2212.03551, https:\/\/doi.org\/10.48550\/arXiv.2212.03551."},{"key":"S2972335325300019BIB033","first-page":"24824","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Wei J.","year":"2022"},{"key":"S2972335325300019BIB034","unstructured":"J. Hoffmann\n                      et al.\n                      , Training compute-optimal large language models, preprint (2022), arXiv:2203.15556, https:\/\/doi.org\/10.48550\/arXiv.2203.15556."},{"key":"S2972335325300019BIB035","unstructured":"J. Wei\n                      et al.\n                      , Emergent abilities of large language models, preprint (2022), arXiv:2206.07682, https:\/\/doi.org\/10.48550\/arXiv.2206.07682."},{"key":"S2972335325300019BIB036","unstructured":"A. Chowdhery\n                      et al.\n                      , PaLM: Scaling language modeling with pathways, preprint (2022), arXiv:2204.02311, https:\/\/doi.org\/10.48550\/arXiv.2204.02311."},{"key":"S2972335325300019BIB037","unstructured":"R. Taylor\n                      et al.\n                      , Galactica: A large language model for science, preprint (2022), arXiv:2211.09085, https:\/\/doi.org\/10.48550\/arXiv.2211.09085."},{"key":"S2972335325300019BIB038","unstructured":"H. Touvron\n                      et al.\n                      , LLaMA: Open and efficient foundation language models, preprint (2023), arXiv:2302.13971, https:\/\/doi.org\/10.48550\/arXiv.2302.13971."},{"key":"S2972335325300019BIB039","unstructured":"DeepSeek-AI\n                      et al.\n                      , DeepSeek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning, preprint (2025), arXiv:2501.12948, https:\/\/doi.org\/10.48550\/arXiv.2501.12948."},{"key":"S2972335325300019BIB040","unstructured":"xAI, Grok 3 beta \u2014 The age of reasoning agents, https:\/\/x.ai\/blog\/grok-3."},{"key":"S2972335325300019BIB041","unstructured":"N. Houlsby\n                      et al.\n                      , Parameter-efficient transfer learning for NLP, preprint (2019), arXiv:1902.00751, https:\/\/doi.org\/10.48550\/arXiv.1902.00751."},{"key":"S2972335325300019BIB042","doi-asserted-by":"crossref","unstructured":"Z. Hu\n                      et al.\n                      , LLM-adapters: An adapter family for parameter-efficient fine-tuning of large language models, preprint (2023), arXiv:2304.01933, https:\/\/doi.org\/10.48550\/arXiv.2304.01933.","DOI":"10.18653\/v1\/2023.emnlp-main.319"},{"key":"S2972335325300019BIB043","unstructured":"J. He, C. Zhou, X. Ma, T. Berg-Kirkpatrick and G.\u00a0Neubig, Towards a unified view of parameter-efficient transfer learning, preprint (2021), arXiv:2110.04366, https:\/\/doi.org\/10.48550\/arXiv.2110.04366."},{"key":"S2972335325300019BIB044","unstructured":"X. L. Li and P. Liang, Prefix-tuning: Optimizing continuous prompts for generation, preprint (2021), arXiv:2101.00190, https:\/\/doi.org\/10.48550\/arXiv.2101.00190."},{"key":"S2972335325300019BIB045","doi-asserted-by":"crossref","unstructured":"X. Liu\n                      et al.\n                      , P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks, preprint (2022), arXiv:2110.07602, https:\/\/doi.org\/10.48550\/arXiv.2110.07602.","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"S2972335325300019BIB046","doi-asserted-by":"crossref","unstructured":"B. Lester, R. Al-Rfou and N. Constant, The power of scale for parameter-efficient prompt tuning, preprint (2021), arXiv:2104.08691, https:\/\/doi.org\/10.48550\/arXiv.2104.08691.","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"S2972335325300019BIB047","unstructured":"X. Liu\n                      et al.\n                      , GPT understands, too, preprint (2023), arXiv:2103.10385, https:\/\/doi.org\/10.48550\/arXiv.2103.10385."},{"key":"S2972335325300019BIB048","unstructured":"E. J. Hu\n                      et al.\n                      , LoRA: Low-rank adaptation of large language models, preprint (2021), arXiv:2106.09685, https:\/\/doi.org\/10.48550\/arXiv.2106.09685."},{"key":"S2972335325300019BIB049","doi-asserted-by":"crossref","unstructured":"M. Valipour, M. Rezagholizadeh, I. Kobyzev and A. Ghodsi, DyLoRA: Parameter efficient tuning of pre-trained models using dynamic search-free low-rank adaptation, preprint (2022), arXiv:2210.07558, https:\/\/doi.org\/10.48550\/arXiv.2210.07558.","DOI":"10.18653\/v1\/2023.eacl-main.239"},{"key":"S2972335325300019BIB050","unstructured":"Q. Zhang\n                      et al.\n                      , AdaLoRA: Adaptive budget allocation for parameter-efficient fine-tuning, preprint (2023), arXiv:2303.10512, https:\/\/doi.org\/10.48550\/arXiv.2303.10512."},{"key":"S2972335325300019BIB051","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2024.09.022"},{"key":"S2972335325300019BIB052","unstructured":"S. Kapoor, B. Stroebl, Z. S. Siegel, N. Nadgir and A. Narayanan, AI agents that matter, preprint (2024), arXiv:2407.01502, https:\/\/doi.org\/10.48550\/arXiv.2407.01502."},{"key":"S2972335325300019BIB053","first-page":"8634","volume-title":"Advances in Neural Information Processing Systems","author":"Shinn N.","year":"2023"},{"key":"S2972335325300019BIB054","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2025.02.012"},{"key":"S2972335325300019BIB055","unstructured":"O. Khattab\n                      et al.\n                      , DSPy: Compiling declarative language model calls into self-improving pipelines, preprint (2023), arXiv:2310.03714, https:\/\/doi.org\/10.48550\/arXiv.2310.03714."},{"key":"S2972335325300019BIB056","unstructured":"A. Radford, K. Narasimhan, T. Salimans, and I. Sutskever, Improving language understanding by generative pre-training, OpenAI Technical Report (2018), https:\/\/cdn.openai.com\/research-covers\/language-unsupervised\/language_understanding_paper.pdf."},{"key":"S2972335325300019BIB057","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.87"},{"key":"S2972335325300019BIB058","unstructured":"Y. Sun, Y. Zheng, C. Hao and H. Qiu, NSP-BERT: A prompt-based few-shot learner through an original pre-training task \u2014 Next sentence prediction, preprint (2022), arXiv:2109.03564, https:\/\/doi.org\/10.48550\/arXiv.2109.03564."},{"key":"S2972335325300019BIB059","doi-asserted-by":"crossref","unstructured":"J. Liu, D. Shen, Y. Zhang, B. Dolan, L. Carin and W. Chen, What makes good in-context examples for GPT-$3$? preprint (2021), arXiv:2101.06804, https:\/\/doi.org\/10.48550\/arXiv.2101.06804.","DOI":"10.18653\/v1\/2022.deelio-1.10"},{"key":"S2972335325300019BIB060","unstructured":"Y. Zhou\n                      et al.\n                      , Large language models are human-level prompt engineers, preprint (2023), arXiv:2211.01910, https:\/\/doi.org\/10.48550\/arXiv.2211.01910."},{"key":"S2972335325300019BIB061","unstructured":"Y. Hao, Y. Sun, L. Dong, Z. Han, Y. Gu and F. Wei, Structured prompting: Scaling in-context learning to 1,000 examples, preprint (2022), arXiv:2212.06713, https:\/\/doi.org\/10.48550\/arXiv.2212.06713."},{"key":"S2972335325300019BIB062","doi-asserted-by":"crossref","unstructured":"Y. Lu, M. Bartolo, A. Moore, S. Riedel and P. Stenetorp, Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity, in\n                      Proc. 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)\n                      (Association for Computational Linguistics, 2022), pp. 8086\u20138098, https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.556.","DOI":"10.18653\/v1\/2022.acl-long.556"},{"key":"S2972335325300019BIB063","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.191"},{"key":"S2972335325300019BIB064","doi-asserted-by":"crossref","unstructured":"X. Ma, Y. Gong, P. He, H. Zhao and N. Duan, Query rewriting for retrieval-augmented large language models, preprint (2023), arXiv:2305.14283, https:\/\/doi.org\/10.48550\/arXiv.2305.14283.","DOI":"10.18653\/v1\/2023.emnlp-main.322"},{"key":"S2972335325300019BIB065","doi-asserted-by":"crossref","unstructured":"L. Gao, X. Ma, J. Lin and J. Callan, Precise zero-shot dense retrieval without relevance labels, preprint (2022), arXiv:2212.10496, https:\/\/doi.org\/10.48550\/arXiv.2212.10496.","DOI":"10.18653\/v1\/2023.acl-long.99"},{"key":"S2972335325300019BIB066","unstructured":"Z. Dai\n                      et al.\n                      , Promptagator: Few-shot dense retrieval from 8 examples, preprint (2022), arXiv:2209.11755, https:\/\/doi.org\/10.48550\/arXiv.2209.11755."},{"key":"S2972335325300019BIB067","unstructured":"O. Khattab\n                      et al.\n                      , Demonstrate\u2013search\u2013predict: Composing retrieval and language models for knowledge-intensive NLP, preprint (2023), arXiv:2212.14024, https:\/\/doi.org\/10.48550\/arXiv.2212.14024."},{"key":"S2972335325300019BIB068","unstructured":"A. Asai, Z. Wu, Y. Wang, A. Sil and H. Hajishirzi, Self-RAG: learning to retrieve, generate, and critique through self-reflection, preprint (2023), arXiv:2310.11511, https:\/\/doi.org\/10.48550\/arXiv.2310.11511."},{"key":"S2972335325300019BIB069","unstructured":"Z. Jiang\n                      et al.\n                      , Active retrieval augmented generation, preprint (2023), arXiv:2305.06983, https:\/\/doi.org\/10.48550\/arXiv.2305.06983."},{"key":"S2972335325300019BIB070","unstructured":"Y. Fu, H. Peng, A. Sabharwal, P. Clark and T. Khot, Complexity-based prompting for multi-step reasoning, preprint (2023), arXiv:2210.00720, https:\/\/doi.org\/10.48550\/arXiv.2210.00720."},{"key":"S2972335325300019BIB071","unstructured":"Z. Zhang, A. Zhang, M. Li and A. Smola, Automatic chain of thought prompting in large language models, preprint (2022), arXiv:2210.03493, https:\/\/doi.org\/10.48550\/arXiv.2210.03493."},{"key":"S2972335325300019BIB072","unstructured":"A. Creswell, M. Shanahan and I. Higgins, Selection-inference: Exploiting large language models for interpretable logical reasoning, preprint (2022), arXiv:2205.09712, https:\/\/doi.org\/10.48550\/arXiv.2205.09712."},{"key":"S2972335325300019BIB073","unstructured":"X. Wang\n                      et al.\n                      , Self-consistency improves chain of thought reasoning in language models, preprint (2023), arXiv:2203.11171, https:\/\/doi.org\/10.48550\/arXiv.2203.11171."},{"key":"S2972335325300019BIB074","doi-asserted-by":"crossref","unstructured":"Y. Li\n                      et al.\n                      , Making large language models better reasoners with step-aware verifier, preprint (2023), arXiv:2206.02336, https:\/\/doi.org\/10.48550\/arXiv.2206.02336.","DOI":"10.18653\/v1\/2023.acl-long.291"},{"key":"S2972335325300019BIB075","unstructured":"X. Wang, J. Wei, D. Schuurmans, Q. Le, E. Chi and D. Zhou, Rationale-augmented ensembles in language models, preprint (2022), arXiv:2207.00747, https:\/\/doi.org\/10.48550\/arXiv.2207.00747."},{"key":"S2972335325300019BIB076","unstructured":"D. Zhou\n                      et al.\n                      , Least-to-most prompting enables complex reasoning in large language models, preprint (2023), arXiv:2205.10625, https:\/\/doi.org\/10.48550\/arXiv.2205.10625."},{"key":"S2972335325300019BIB077","unstructured":"T. Khot\n                      et al.\n                      , Decomposed prompting: A modular approach for solving complex tasks, preprint (2023), arXiv:2210.02406, https:\/\/doi.org\/10.48550\/arXiv.2210.02406."},{"key":"S2972335325300019BIB078","unstructured":"Q. Lyu\n                      et al.\n                      , Faithful chain-of-thought reasoning, preprint (2023), arXiv:2301.13379, https:\/\/doi.org\/10.48550\/arXiv.2301.13379."},{"key":"S2972335325300019BIB079","unstructured":"L. Gao\n                      et al.\n                      , PAL: Program-aided language models, preprint (2023), arXiv:2211.10435, https:\/\/doi.org\/10.48550\/arXiv.2211.10435."},{"key":"S2972335325300019BIB080","unstructured":"Y. Shen, K. Song, X. Tan, D. Li, W. Lu and Y. Zhuang, HuggingGPT: Solving AI tasks with ChatGPT and its friends in Hugging Face, preprint (2023), arXiv:2303.17580, https:\/\/doi.org\/10.48550\/arXiv.2303.17580."},{"key":"S2972335325300019BIB081","unstructured":"H. Sun, Y. Zhuang, L. Kong, B. Dai and C. Zhang, AdaPlanner: Adaptive planning from feedback with language models, preprint (2023), arXiv:2305.16653, https:\/\/doi.org\/10.48550\/arXiv.2305.16653."},{"key":"S2972335325300019BIB082","doi-asserted-by":"crossref","unstructured":"Y. Lu, P. Lu, Z. Chen, W. Zhu, X. E. Wang and W. Y. Wang, Multimodal procedural planning via dual text-image prompting, preprint (2023), arXiv:2305.01795, https:\/\/doi.org\/10.48550\/arXiv.2305.01795.","DOI":"10.18653\/v1\/2024.findings-emnlp.641"},{"key":"S2972335325300019BIB083","unstructured":"S. Hao\n                      et al.\n                      , Reasoning with language model is planning with world model, preprint (2023), arXiv:2305.14992, https:\/\/doi.org\/10.48550\/arXiv.2305.14992."},{"key":"S2972335325300019BIB084","doi-asserted-by":"crossref","unstructured":"Z. Chen, K. Zhou, B. Zhang, Z. Gong, W. X. Zhao and J.R. Wen, ChatCoT: Tool-augmented chain-of-thought reasoning on chat-based large language models, preprint (2023), arXiv:2305.14323, https:\/\/doi.org\/10.48550\/arXiv.2305.14323.","DOI":"10.18653\/v1\/2023.findings-emnlp.985"},{"key":"S2972335325300019BIB085","unstructured":"S. Yao\n                      et al.\n                      , ReAct: Synergizing reasoning and acting in language models, preprint (2023), arXiv:2210.03629, https:\/\/doi.org\/10.48550\/arXiv.2210.03629."},{"key":"S2972335325300019BIB086","unstructured":"N. Shinn, F. Cassano, E. Berman, A. Gopinath, K. Narasimhan and S. Yao, Reflexion: Language agents with verbal reinforcement learning, preprint (2023), arXiv:2303.11366, https:\/\/doi.org\/10.48550\/arXiv.2303.11366."},{"key":"S2972335325300019BIB087","unstructured":"S. Yao\n                      et al.\n                      , Tree of thoughts: Deliberate problem solving with large language models, preprint (2023), arXiv:2305.10601, https:\/\/doi.org\/10.48550\/arXiv.2305.10601."},{"key":"S2972335325300019BIB088","doi-asserted-by":"publisher","DOI":"10.1016\/j.health.2023.100198"},{"key":"S2972335325300019BIB089","doi-asserted-by":"publisher","DOI":"10.1002\/qub2.67"},{"key":"S2972335325300019BIB090","doi-asserted-by":"publisher","DOI":"10.1142\/S2972335324500054"},{"key":"S2972335325300019BIB091","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.6b00740"},{"key":"S2972335325300019BIB092","unstructured":"R. Tang, X. Han, X. Jiang and X. Hu, Does synthetic data generation of LLMs help clinical text mining? preprint (2023), arXiv:2303.04360, https:\/\/doi.org\/10.48550\/arXiv.2303.04360."},{"key":"S2972335325300019BIB093","doi-asserted-by":"crossref","unstructured":"O. Nov, N. Singh and D. Mann, Putting ChatGPT\u2019s medical advice to the (Turing) test, preprint (2023), arXiv:2301.10035, https:\/\/doi.org\/10.48550\/arXiv.2301.10035.","DOI":"10.2196\/preprints.46939"},{"key":"S2972335325300019BIB094","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.370"},{"key":"S2972335325300019BIB095","unstructured":"K. Jeblick\n                      et al.\n                      , ChatGPT makes medicine easy to swallow: An exploratory case study on simplified radiology reports, preprint (2022), arXiv:2212.14882, https:\/\/doi.org\/10.48550\/arXiv.2212.14882."},{"key":"S2972335325300019BIB096","unstructured":"K. Singhal\n                      et al.\n                      , Large language models encode clinical knowledge, preprint (2022), arXiv:2212.13138, https:\/\/doi.org\/10.48550\/arXiv.2212.13138."},{"key":"S2972335325300019BIB097","unstructured":"K. Singhal\n                      et al.\n                      , Towards expert-level medical question answering with large language models, preprint (2023), arXiv:2305.09617, https:\/\/doi.org\/10.48550\/arXiv.2305.09617."},{"key":"S2972335325300019BIB098","doi-asserted-by":"crossref","unstructured":"S. Yang\n                      et al.\n                      , Zhongjing: Enhancing the Chinese medical capabilities of large language model through expert feedback and real-world multi-turn dialogue, preprint (2023), arXiv:2308.03549, https:\/\/doi.org\/10.48550\/arXiv.2308.03549.","DOI":"10.1609\/aaai.v38i17.29907"},{"key":"S2972335325300019BIB099","doi-asserted-by":"crossref","unstructured":"S. Chen\n                      et al.\n                      , The utility of ChatGPT for cancer treatment information, preprint (2023), https:\/\/doi.org\/10.1101\/2023.03.16.23287316.","DOI":"10.1101\/2023.03.16.23287316"},{"key":"S2972335325300019BIB100","doi-asserted-by":"publisher","DOI":"10.1001\/jamainternmed.2023.1838"},{"key":"S2972335325300019BIB101","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMsr2214184"},{"key":"S2972335325300019BIB102","doi-asserted-by":"publisher","DOI":"10.2196\/46599"},{"key":"S2972335325300019BIB103","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2023.1044"},{"key":"S2972335325300019BIB104","doi-asserted-by":"crossref","unstructured":"A. J. Nastasi, K. R. Courtright, S. D. Halpern and G. E. Weissman, Does ChatGPT provide appropriate and equitable medical advice? A vignette-based, clinical evaluation across care contexts, preprint (2023), https:\/\/doi.org\/10.1101\/2023.02.25.23286451.","DOI":"10.1101\/2023.02.25.23286451"},{"key":"S2972335325300019BIB105","doi-asserted-by":"crossref","unstructured":"A. Rao\n                      et al.\n                      , Assessing the utility of ChatGPT throughout the entire clinical workflow, preprint (2023), https:\/\/doi.org\/10.1101\/2023.02.21.23285886.","DOI":"10.2196\/preprints.48659"},{"key":"S2972335325300019BIB106","doi-asserted-by":"crossref","unstructured":"D. M. Levine\n                      et al.\n                      , The diagnostic and triage accuracy of the GPT-3 artificial intelligence model, preprint (2023), https:\/\/doi.org\/10.1101\/2023.01.30.23285067.","DOI":"10.1101\/2023.01.30.23285067"},{"key":"S2972335325300019BIB107","doi-asserted-by":"publisher","DOI":"10.1145\/3587102.3588827"},{"key":"S2972335325300019BIB108","unstructured":"T. Susnjak, ChatGPT: The end of online exam integrity? preprint (2022), arXiv:2212.09292, https:\/\/doi.org\/10.48550\/arXiv.2212.09292."},{"key":"S2972335325300019BIB109","unstructured":"K. Tan, T. Pang, C. Fan and S. Yu, Towards applying powerful large AI models in classroom teaching: Opportunities, challenges and prospects, preprint (2023), arXiv:2305.03433, https:\/\/doi.org\/10.48550\/arXiv.2305.03433."},{"key":"S2972335325300019BIB110","doi-asserted-by":"crossref","unstructured":"F. Kamalov, D. S. Calong and I. Gurrib, New era of artificial intelligence in education: Towards a sustainable multifaceted revolution, preprint (2023), arXiv:2305.18303, https:\/\/doi.org\/10.48550\/arXiv.2305.18303.","DOI":"10.3390\/su151612451"},{"key":"S2972335325300019BIB111","doi-asserted-by":"crossref","unstructured":"E. Kasneci\n                      et al.\n                      , ChatGPT for good? On opportunities and challenges of large language models for education,\n                      Learn. Individ. Differ.\n                      103\n                      (2023)102274, https:\/\/doi.org\/10.1016\/j.lindif.2023.102274.","DOI":"10.1016\/j.lindif.2023.102274"},{"key":"S2972335325300019BIB112","doi-asserted-by":"publisher","DOI":"10.3934\/QFE.2021032"},{"key":"S2972335325300019BIB113","doi-asserted-by":"crossref","unstructured":"A. Shah and S. Chava, Zero is not hero yet: Benchmarking zero-shot performance of LLMs for financial tasks, preprint (2023), arXiv:2305.16633, https:\/\/doi.org\/10.48550\/arXiv.2305.16633.","DOI":"10.2139\/ssrn.4458613"},{"key":"S2972335325300019BIB114","unstructured":"D. Araci, FinBERT: Financial sentiment analysis with pre-trained language models, preprint (2019), arXiv:1908.10063, https:\/\/doi.org\/10.48550\/arXiv.1908.10063."},{"key":"S2972335325300019BIB115","first-page":"84","volume-title":"Proc. Australasian Language Technology Association Workshop 2015","author":"Salinas Alvarado J. C.","year":"2015"},{"key":"S2972335325300019BIB116","unstructured":"G. Son, H. Jung, M. Hahm, K. Na and S. Jin, Beyond classification: Financial reasoning in state-of-the-art language models, preprint (2023), arXiv:2305.01505, https:\/\/doi.org\/10.48550\/arXiv.2305.01505."},{"key":"S2972335325300019BIB117","unstructured":"S. Wu\n                      et al.\n                      , BloombergGPT: A large language model for finance, preprint (2023), arXiv:2303.17564, https:\/\/doi.org\/10.48550\/arXiv.2303.17564."},{"key":"S2972335325300019BIB118","doi-asserted-by":"crossref","unstructured":"X. Zhang, Q. Yang and D. Xu, XuanYuan 2.0: A large Chinese financial chat model with hundreds of billions parameters, preprint (2023), arXiv:2305.12002, https:\/\/doi.org\/10.48550\/arXiv.2305.12002.","DOI":"10.1145\/3583780.3615285"},{"key":"S2972335325300019BIB119","doi-asserted-by":"crossref","unstructured":"H. Yang, X.Y. Liu and C. D. Wang, FinGPT: Open-source financial large language models, preprint (2023), arXiv:2306.06031, https:\/\/doi.org\/10.48550\/arXiv.2306.06031.","DOI":"10.2139\/ssrn.4489826"},{"key":"S2972335325300019BIB120","unstructured":"N. Carlini and D. Wagner, Towards evaluating the robustness of neural networks, preprint (2017), arXiv:1608.04644, http:\/\/arxiv.org\/abs\/1608.04644."},{"key":"S2972335325300019BIB121","doi-asserted-by":"publisher","DOI":"10.1016\/j.jaad.2024.10.127"},{"key":"S2972335325300019BIB122","unstructured":"X. Zhang, J. Zhao and Y. LeCun, Character-level convolutional networks for text classification, preprint (2016), arXiv:1509.01626, http:\/\/arxiv.org\/abs\/1509.01626."},{"key":"S2972335325300019BIB123","unstructured":"Z. C. Lipton, The mythos of model interpretability, preprint (2017), arXiv:1606.03490, http:\/\/arxiv.org\/abs\/1606.03490."},{"key":"S2972335325300019BIB124","doi-asserted-by":"crossref","unstructured":"J. Jiang, K. Zhou, Z. Dong, K. Ye, W. X. Zhao and J.R. Wen, StructGPT: A general framework for large language model to reason over structured data, preprint (2023), arXiv:2305.09645, https:\/\/doi.org\/10.48550\/arXiv.2305.09645.","DOI":"10.18653\/v1\/2023.emnlp-main.574"},{"key":"S2972335325300019BIB125","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.39"},{"key":"S2972335325300019BIB126","first-page":"109","volume-title":"Psychology of Learning and Motivation","volume":"24","author":"McCloskey M.","year":"1989"},{"key":"S2972335325300019BIB127","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11651"},{"key":"S2972335325300019BIB128","unstructured":"Y. Bang\n                      et al.\n                      , A multitask, multilingual, multimodal evaluation of ChatGPT on reasoning, hallucination, and interactivity, preprint (2023), arXiv:2302.04023, https:\/\/doi.org\/10.48550\/arXiv.2302.04023."},{"key":"S2972335325300019BIB129","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"S2972335325300019BIB130","doi-asserted-by":"crossref","unstructured":"Y. Li, Y. Du, K. Zhou, J. Wang, W. X. Zhao and J.R. Wen, Evaluating object hallucination in large vision-language models, preprint (2023), arXiv:2305.10355, https:\/\/doi.org\/10.48550\/arXiv.2305.10355.","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"S2972335325300019BIB131","unstructured":"B. Peng\n                      et al.\n                      , Check your facts and try again: Improving large language models with external knowledge and automated feedback, preprint (2023), arXiv:2302.12813, https:\/\/doi.org\/10.48550\/arXiv.2302.12813."},{"key":"S2972335325300019BIB132","unstructured":"A. Lazaridou, E. Gribovskaya, W. Stokowiec and N. Grigorev, Internet-augmented language models through few-shot prompting for open-domain question answering, preprint (2022), arXiv:2203.05115, https:\/\/doi.org\/10.48550\/arXiv.2203.05115."},{"key":"S2972335325300019BIB133","unstructured":"H. Qian\n                      et al.\n                      , WebBrain: Learning to generate factually correct articles for queries by grounding on large web corpus, preprint (2023), arXiv:2304.04358, https:\/\/doi.org\/10.48550\/arXiv.2304.04358."},{"key":"S2972335325300019BIB134","unstructured":"J. Liu, J. Jin, Z. Wang, J. Cheng, Z. Dou and J.R. Wen, RETA-LLM: A retrieval-augmented large language model toolkit, preprint (2023), arXiv:2306.05212, https:\/\/doi.org\/10.48550\/arXiv.2306.05212."},{"key":"S2972335325300019BIB135","doi-asserted-by":"crossref","unstructured":"D. Dai, L. Dong, Y. Hao, Z. Sui, B. Chang and F. Wei,Knowledge neurons in pretrained transformers, in\n                      Proc. 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)\n                      (Association for Computational Linguistics, 2022), pp. 8493\u20138502, https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.581.","DOI":"10.18653\/v1\/2022.acl-long.581"},{"key":"S2972335325300019BIB136","first-page":"17359","volume-title":"Advances in Neural Information Processing Systems","author":"Meng K.","year":"2022"},{"key":"S2972335325300019BIB137","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.446"},{"key":"S2972335325300019BIB138","unstructured":"Y. Yao\n                      et al.\n                      , Editing large language models: Problems, methods, and opportunities, preprint (2023), arXiv:2305.13172, https:\/\/doi.org\/10.48550\/arXiv.2305.13172."},{"key":"S2972335325300019BIB139","unstructured":"J. Uesato\n                      et al.\n                      , Solving math word problems with process- and outcome-based feedback, preprint (2022), arXiv:2211.14275, https:\/\/doi.org\/10.48550\/arXiv.2211.14275."},{"key":"S2972335325300019BIB140","unstructured":"H. Lightman\n                      et al.\n                      , Let\u2019s verify step by step, preprint (2023), arXiv:2305.20050, https:\/\/doi.org\/10.48550\/arXiv.2305.20050."},{"key":"S2972335325300019BIB141","unstructured":"Z. Gou\n                      et al.\n                      , CRITIC: Large language models can self-correct with tool-interactive critiquing, preprint (2024), arXiv:2305.11738, https:\/\/doi.org\/10.48550\/arXiv.2305.11738."},{"key":"S2972335325300019BIB142","doi-asserted-by":"crossref","unstructured":"Z. Shao, Y. Gong, Y. Shen, M. Huang, N. Duan and W. Chen, Enhancing retrieval-augmented large language models with iterative retrieval-generation synergy, preprint (2023), arXiv:2305.15294, https:\/\/doi.org\/10.48550\/arXiv.2305.15294.","DOI":"10.18653\/v1\/2023.findings-emnlp.620"},{"key":"S2972335325300019BIB143","doi-asserted-by":"crossref","unstructured":"P. Lu, L. Qiu, W. Yu, S. Welleck and K.W. Chang, A survey of deep learning for mathematical reasoning, preprint (2023), arXiv:2212.10535, https:\/\/doi.org\/10.48550\/arXiv.2212.10535.","DOI":"10.18653\/v1\/2023.acl-long.817"},{"key":"S2972335325300019BIB144","unstructured":"J. Qian, H. Wang, Z. Li, S. Li and X. Yan, Limitations of language models in arithmetic and symbolic induction, preprint (2022), arXiv:2208.05051, https:\/\/doi.org\/10.48550\/arXiv.2208.05051."},{"key":"S2972335325300019BIB145","unstructured":"Z. Yuan, H. Yuan, C. Tan, W. Wang and S. Huang, How well do large language models perform in arithmetic tasks? preprint (2023), arXiv:2304.02015, https:\/\/doi.org\/10.48550\/arXiv.2304.02015."},{"key":"S2972335325300019BIB146","unstructured":"T. Liu and B. K. H. Low, Goat: Fine-tuned LLaMA outperforms GPT-4 on arithmetic tasks, preprint (2023), arXiv:2305.14201, https:\/\/doi.org\/10.48550\/arXiv.2305.14201."},{"key":"S2972335325300019BIB147","unstructured":"A. Gu and T. Dao, Mamba: Linear-time sequence modeling with selective state spaces, preprint (2024), arXiv:2312.00752, http:\/\/arxiv.org\/abs\/2312.00752."}],"container-title":["International Journal of Artificial Intelligence and Robotics Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S2972335325300019","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T04:11:09Z","timestamp":1768363869000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S2972335325300019"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":147,"alternative-id":["10.1142\/S2972335325300019"],"URL":"https:\/\/doi.org\/10.1142\/s2972335325300019","relation":{},"ISSN":["2972-3353","2972-3361"],"issn-type":[{"value":"2972-3353","type":"print"},{"value":"2972-3361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"article-number":"2530001"}}