{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T16:35:53Z","timestamp":1776357353728,"version":"3.51.2"},"reference-count":259,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T00:00:00Z","timestamp":1734480000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T00:00:00Z","timestamp":1734480000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Prog Artif Intell"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s13748-024-00359-4","type":"journal-article","created":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T14:04:15Z","timestamp":1734530655000},"page":"117-164","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["The role of large language models in agriculture: harvesting the future with LLM intelligence"],"prefix":"10.1007","volume":"14","author":[{"given":"Tawseef Ayoub","family":"Shaikh","sequence":"first","affiliation":[]},{"given":"Tabasum","family":"Rasool","sequence":"additional","affiliation":[]},{"given":"K.","family":"Veningston","sequence":"additional","affiliation":[]},{"given":"Syed Mufassir","family":"Yaseen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,18]]},"reference":[{"key":"359_CR1","first-page":"1","volume":"222","author":"J Li","year":"2023","unstructured":"Li, J., Xu, M., Xiang, L., Chen, D., Zhuang, W., Yin, X., Li, Z.: Foundation models in smart agriculture: basics, opportunities, and challenges. Comput. Electron. Agric. 222, 1\u201316 (2023)","journal-title":"Comput. Electron. Agric."},{"key":"359_CR2","doi-asserted-by":"publisher","first-page":"102692","DOI":"10.1016\/j.artmed.2023.102692","volume":"146","author":"TA Shaikh","year":"2023","unstructured":"Shaikh, T.A., Rasool, T., Verma, P.: Machine intelligence and medical cyber-physical system architectures for smart healthcare: taxonomy, challenges, opportunities, and possible solutions. Artif. Intell. Med. 146, 102692 (2023)","journal-title":"Artif. Intell. Med."},{"key":"359_CR3","doi-asserted-by":"publisher","first-page":"107119","DOI":"10.1016\/j.compag.2022.107119","volume":"19","author":"TA Shaikh","year":"2022","unstructured":"Shaikh, T.A., Rasool, T., Lone, F.R.: Towards leveraging the role of machine learning and artificial intelligence in precision agriculture and smart farming. Comput. Electron. Agric. 19, 107119 (2022)","journal-title":"Comput. Electron. Agric."},{"key":"359_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2022.107389","volume":"202","author":"X Zhou","year":"2022","unstructured":"Zhou, X., Ampatzidis, Y., Lee, W.S., Zhou, C., Agehara, S., Schueller, J.K.: Deep learning-based postharvest strawberry bruise detection under uv and incandescent light. Comput. Electron. Agric. 202, 107389 (2022)","journal-title":"Comput. Electron. Agric."},{"key":"359_CR5","doi-asserted-by":"publisher","first-page":"106775","DOI":"10.1016\/j.knosys.2021.106775","volume":"216","author":"C Zhang","year":"2021","unstructured":"Zhang, C., Xie, Y., Bai, H., Yu, B., Li, W., Gao, Y.: A survey on federated learning. Knowl. Based Syst. 216, 106775 (2021)","journal-title":"Knowl. Based Syst."},{"issue":"1","key":"359_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13007-022-00866-2","volume":"18","author":"J Yang","year":"2022","unstructured":"Yang, J., Guo, X., Li, Y., Marinello, F., Ercisli, S., Zhang, Z.: A survey of few-shot learning in smart agriculture: developments, applications, and challenges. Plant Methods 18(1), 1\u201312 (2022)","journal-title":"Plant Methods"},{"key":"359_CR7","doi-asserted-by":"publisher","first-page":"108412","DOI":"10.1016\/j.compag.2023.108412","volume":"215","author":"J Li","year":"2023","unstructured":"Li, J., Chen, D., Qi, X., Li, Z., Huang, Y., Morris, D., Tan, X.: Label-efficient learning in agriculture: a comprehensive review. Comput. Electron. Agric. 215, 108412 (2023). https:\/\/doi.org\/10.1016\/j.compag.2023.108412","journal-title":"Comput. Electron. Agric."},{"key":"359_CR8","unstructured":"Go\u00ebau, H., Bonnet, P., Joly, A.: Overview of plantclef 2022: image-based plant identification at global scale. In CLEF 2022-Conference and Labs of the Evaluation Forum, 3180: 1916\u20131928. (2022)"},{"issue":"7956","key":"359_CR9","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","volume":"616","author":"M Moor","year":"2023","unstructured":"Moor, M., Banerjee, O., Abad, Z.S.H., Krumholz, H.M., Leskovec, J., Topol, E.J., Rajpurkar, P.: Foundation models for generalist medical artificial intelligence. Nature 616(7956), 259\u2013265 (2023)","journal-title":"Nature"},{"key":"359_CR10","unstructured":"Minaee, S., Mikolov, T., Nikzad, N., Chenaghlu, M., Socher, R., Amatriain, X. Gao, J.: Large language models: a survey, arXiv:2402.06196v2 [cs.CL], pp. 1\u201343, (2024)"},{"key":"359_CR11","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y. Doll\u00e1r, P.: Segment anything, rXiv preprint arXiv:2304.02643, (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"issue":"01","key":"359_CR12","doi-asserted-by":"publisher","first-page":"2500","DOI":"10.20546\/ijcmas.2019.801.264","volume":"8","author":"S Ahirwar","year":"2019","unstructured":"Ahirwar, S., Swarnkar, R., Bhukya, S., Namwade, G.: Application of drone in agriculture. Int. J. Curr. Microbiol. Appl. Sci. 8(01), 2500\u20132505 (2019)","journal-title":"Int. J. Curr. Microbiol. Appl. Sci."},{"key":"359_CR13","doi-asserted-by":"publisher","first-page":"108270","DOI":"10.1016\/j.compag.2023.108270","volume":"214","author":"F Visentin","year":"2023","unstructured":"Visentin, F., Cremasco, S., Sozzi, M., Signorini, L., Signorini, M., Marinello, F., Muradore, R.: A mixed-autonomous robotic platform for intra-row and inter-row weed removal for precision agriculture. Comput. Electron. Agric. 214, 108270 (2023). https:\/\/doi.org\/10.1016\/j.compag.2023.108270","journal-title":"Comput. Electron. Agric."},{"key":"359_CR14","doi-asserted-by":"publisher","first-page":"4097","DOI":"10.1109\/ACCESS.2020.3041597","volume":"9","author":"N Abdullah","year":"2021","unstructured":"Abdullah, N.: Towards smart agriculture monitoring using fuzzy systems. IEEE Access 9, 4097\u20134111 (2021)","journal-title":"IEEE Access"},{"key":"359_CR15","doi-asserted-by":"publisher","unstructured":"Saleheen, M.M., Islam, M.S., Fahad, R., Belal, M.J., Khan, R.: IoT-Based smart agriculture monitoring system. In: Proceedings of IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET), Kota Kinabalu, Malaysia, pp. 1\u20136, (2022), https:\/\/doi.org\/10.1109\/IICAIET55139.2022.9936826","DOI":"10.1109\/IICAIET55139.2022.9936826"},{"key":"359_CR16","unstructured":"Team, A.A., Bauer, J., Baumli, K., Baveja, S., Behbahani, F., Bhoopchand, A., Bradley-Schmieg, N., Chang, M., Clay, N., Collister, A. Dasagi, V.: Human timescale adaptation in an open-ended task space\u201d arXiv preprint arXiv:2301.07608, (2023)"},{"key":"359_CR17","doi-asserted-by":"publisher","first-page":"1095","DOI":"10.1016\/j.tplants.2023.06.016","volume":"28","author":"A Geitmann","year":"2023","unstructured":"Geitmann, A., Bidhendi, A.J.: Plant blindness and diversity in AI language models. Trends Plant Sci. 28, 1095\u20131097 (2023)","journal-title":"Trends Plant Sci."},{"key":"359_CR18","doi-asserted-by":"publisher","first-page":"100041","DOI":"10.1016\/j.dajour.2022.100041","volume":"3","author":"S Kumar","year":"2022","unstructured":"Kumar, S., Durai, S., Shamili, M.D.: Smart farming using machine learning and deep learning techniques. Decis. Anal. J. 3, 100041 (2022)","journal-title":"Decis. Anal. J."},{"key":"359_CR19","doi-asserted-by":"publisher","first-page":"108453","DOI":"10.1016\/j.compeleceng.2022.108453","volume":"104","author":"DA Gzar","year":"2022","unstructured":"Gzar, D.A., Mahmood, A.M., Adilee, M.K.A.: Recent trends of smart agricultural systems based on Internet of Things technology: a survey. Comput. Electr. Eng. 104, 108453 (2022)","journal-title":"Comput. Electr. Eng."},{"key":"359_CR20","doi-asserted-by":"publisher","unstructured":"Vocaturo, E., Rani, G., Dhaka, V.S., Zumpano, E.: AI-driven agriculture: opportunities and challenges. In: 2023 IEEE International Conference on Big Data (BigData) | 979-8-3503-2445-7\/23\/$31.00 \u00a92023 IEEE, https:\/\/doi.org\/10.1109\/BigData59044.2023.10386314","DOI":"10.1109\/BigData59044.2023.10386314"},{"issue":"6","key":"359_CR21","doi-asserted-by":"publisher","first-page":"1554","DOI":"10.1214\/aoms\/1177699147","volume":"37","author":"LE Baum","year":"1966","unstructured":"Baum, L.E., Petrie, T.: Statistical inference for probabilistic functions of finite state Markov chains. Ann. Math. Stat. 37(6), 1554\u20131563 (1966)","journal-title":"Ann. Math. Stat."},{"issue":"3","key":"359_CR22","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1109\/TASSP.1987.1165125","volume":"35","author":"S Katz","year":"1987","unstructured":"Katz, S.: Estimation of probabilities from sparse data for the language model component of a speech recognizer. IEEE Trans. Acoust. Speech Signal Process. 35(3), 400\u2013401 (1987)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"3","key":"359_CR23","first-page":"1045","volume":"2","author":"T Mikolov","year":"2010","unstructured":"Mikolov, T., Karafi\u00e1t, M., Burget, L.: Recurrent neural network based language model. Interspeech. 2(3), 1045\u20131048 (2010)","journal-title":"Interspeech."},{"key":"359_CR24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1142\/9789812813312_0001","volume":"13","author":"Y Bengio","year":"2000","unstructured":"Bengio, Y., Ducharme, R., Vincent, P.A.: Neural probabilistic language model. Adv. Neural. Inf. Process. Syst. 13, 1\u201314 (2000)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"359_CR25","first-page":"194","volume":"2012","author":"M Sundermeyer","year":"2012","unstructured":"Sundermeyer, M., Schl\u00fcter, R., Ney, H.: Lstm neural networks for language modelling. Interspeech. 2012, 194\u2013197 (2012)","journal-title":"Interspeech."},{"key":"359_CR26","doi-asserted-by":"publisher","unstructured":"Peters, M., Neumann, M., Iyyer, M. :Deep contextualized word representations ArXiv. (2018). https:\/\/doi.org\/10.48550\/arXiv.1802.05365","DOI":"10.48550\/arXiv.1802.05365"},{"key":"359_CR27","unstructured":"Vaswani, A., Shazeer, N., Parmar N.: Attention is all you need. Advances in neural information processing systems. (2017), 30."},{"issue":"2","key":"359_CR28","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1145\/3624724","volume":"67","author":"M Shanahan","year":"2000","unstructured":"Shanahan, M.: Talking about large language models. Commun. ACM 67(2), 68\u201379 (2000)","journal-title":"Commun. ACM"},{"key":"359_CR29","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks, Advances in Neural Information Processing Systems, vol. 25, pp. 1\u201325, (2012)"},{"key":"359_CR30","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, vol. 25, pp. 1\u201317, (2012)"},{"key":"359_CR31","doi-asserted-by":"publisher","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. ArXiv. (2014). https:\/\/doi.org\/10.48550\/arXiv.1409.1556","DOI":"10.48550\/arXiv.1409.1556"},{"key":"359_CR32","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on computer vision and Pattern Recognition, pp. 1\u20139, (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"359_CR33","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 35: 770\u2013778"},{"key":"359_CR34","first-page":"1","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R.: Faster r-cnn: towards real-time object detection with region proposal networks. Adv. Neural. Inf. Process. Syst. 28, 1\u201318 (2015)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"359_CR35","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R..: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788, (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"359_CR36","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P.: \u201cMask r-cnn\u201d. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969, (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"359_CR37","doi-asserted-by":"publisher","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A.: An image is worth 16 \u00d7 16 words: transformers for image recognition at scale\u201d ArXiv. (2020). https:\/\/doi.org\/10.48550\/arXiv.2010.11929","DOI":"10.48550\/arXiv.2010.11929"},{"key":"359_CR38","unstructured":"Ramesh, A., Pavlov, M., Oh, G.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831, (2021)"},{"key":"359_CR39","doi-asserted-by":"crossref","unstructured":"Wu, J., Gan, W., Chen, Z.: Multimodal large language models: a survey. In: 2023 IEEE International Conference on Big Data (BigData), pp. 2247\u20132256, (2023)","DOI":"10.1109\/BigData59044.2023.10386743"},{"key":"359_CR40","doi-asserted-by":"publisher","unstructured":"Hoffmann, J., Borgeaud, S., Mensch, A.: Training compute-optimal large language models. ArXiv. (2022) https:\/\/doi.org\/10.48550\/arXiv.2203.15556","DOI":"10.48550\/arXiv.2203.15556"},{"key":"359_CR41","doi-asserted-by":"publisher","unstructured":"Le Scao, T., Fan, A., Akiki, C.: Bloom: a 176b-parameter open-access multilingual language model. ArXiv. (2023). https:\/\/doi.org\/10.48550\/arXiv.2211.05100","DOI":"10.48550\/arXiv.2211.05100"},{"key":"359_CR42","doi-asserted-by":"publisher","unstructured":"Anil, R., Dai, A., Firat, O.: Palm 2 technical report\u201d ArXiv. (2023) https:\/\/doi.org\/10.48550\/arXiv.2305.10403","DOI":"10.48550\/arXiv.2305.10403"},{"key":"359_CR43","doi-asserted-by":"publisher","unstructured":"Zhang, S., Roller, S., Goyal, N.: Opt: open pre-trained transformer language models. ArXiv. (2022) https:\/\/doi.org\/10.48550\/arXiv.2205.01068","DOI":"10.48550\/arXiv.2205.01068"},{"key":"359_CR44","doi-asserted-by":"publisher","unstructured":"Zhu, D., Chen, J., Shen, X.: Minigpt-4: enhancing vision-language understanding with advanced large language models\u201d ArXiv. (2023). https:\/\/doi.org\/10.48550\/arXiv.2304.10592","DOI":"10.48550\/arXiv.2304.10592"},{"issue":"1","key":"359_CR45","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2023.100005","volume":"1","author":"L Zhao","year":"2023","unstructured":"Zhao, L., Zhang, L., Wu, Z.: When brain-inspired ai meets agi. Meta-Radiology 1(1), 100005 (2023)","journal-title":"Meta-Radiology"},{"key":"359_CR46","doi-asserted-by":"publisher","unstructured":"Bubeck, S., Chandrasekaran, V., Eldan, R.: Sparks of artificial general intelligence: early experiments with gpt-4\u201d, ArXiv. (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.12712","DOI":"10.48550\/arXiv.2303.12712"},{"key":"359_CR47","doi-asserted-by":"publisher","unstructured":"Gao, P., Han, J., Zhang, R.: Llama-adapter v2: parameter-efficient visual instruction model. ArXiv. (2023). https:\/\/doi.org\/10.48550\/arXiv.2304.15010.","DOI":"10.48550\/arXiv.2304.15010"},{"key":"359_CR48","doi-asserted-by":"publisher","unstructured":"Team, G., Anil, R., Borgeaud, S.: Gemini: a family of highly capable multimodal models. ArXiv. (2023). https:\/\/doi.org\/10.48550\/arXiv.2312.11805","DOI":"10.48550\/arXiv.2312.11805"},{"key":"359_CR49","doi-asserted-by":"crossref","unstructured":"Girdhar, R, El-Nouby, R.A., Liu, Z.: Imagebind: one embedding space to bind them all. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15180\u201315190, (2023)","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"359_CR50","doi-asserted-by":"publisher","unstructured":"Wu, C., Lin, W., Zhang, X.: PMC-LLaMA: toward building open-source language models for medicine ArXiv. (2023) https:\/\/doi.org\/10.48550\/arXiv.2305.10415.","DOI":"10.48550\/arXiv.2305.10415"},{"key":"359_CR51","doi-asserted-by":"publisher","unstructured":"Driess, D., Xia, F., Sajjadi, M.S.M.: Palm-e: an embodied multimodal language model\u201d ArXiv. (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.03378.","DOI":"10.48550\/arXiv.2303.03378"},{"key":"359_CR52","doi-asserted-by":"publisher","unstructured":"Bai, J., Bai, S., Yang, S.: Qwen-vl: a frontier large vision-language model with versatile abilities ArXiv. (2023). https:\/\/doi.org\/10.48550\/arXiv.2308.12966.","DOI":"10.48550\/arXiv.2308.12966"},{"key":"359_CR53","doi-asserted-by":"publisher","unstructured":"Wu, S., Irsoy, O., Lu, S.: Bloomberggpt: a large language model for finance. ArXiv. (2023) https:\/\/doi.org\/10.48550\/arXiv.2303.17564.","DOI":"10.48550\/arXiv.2303.17564"},{"key":"359_CR54","doi-asserted-by":"publisher","unstructured":"Bi, Z., Zhang, N., Xue, Y.: Oceangpt: a large language model for ocean science tasks ArXiv. (2023) https:\/\/doi.org\/10.48550\/arXiv.2310.02031.","DOI":"10.48550\/arXiv.2310.02031"},{"key":"359_CR55","doi-asserted-by":"crossref","unstructured":"Wang, W., Dai, J., Chen, Z.: Internimage: exploring large-scale vision foundation models with deformable convolutions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14408\u201314419, (2023)","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"359_CR56","first-page":"1","volume":"36","author":"H Liu","year":"2024","unstructured":"Liu, H., Li, C., Wu, Q.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 1\u201317 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"359_CR57","unstructured":"Dai, W., Li, J., Li, D.: Instructblip: towards general-purpose vision-language models with instruction tuning. Advances in Neural Information Processing Systems, vol. 36, pp. 1\u2013121, (2024)"},{"key":"359_CR58","doi-asserted-by":"publisher","unstructured":"Wu, C., Yin, S., Qi, W.: Visual chatgpt: talking, drawing and editing with visual foundation models\u201d ArXiv. (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.04671","DOI":"10.48550\/arXiv.2303.04671"},{"key":"359_CR59","doi-asserted-by":"publisher","unstructured":"Ye, Q., Xu, H., Xu, G.: mplug-owl: modularization empowers large language models with multimodality. ArXiv. https:\/\/doi.org\/10.48550\/arXiv.2304.14178. 666, (2023)","DOI":"10.48550\/arXiv.2304.14178"},{"key":"359_CR60","first-page":"1","volume":"36","author":"S Huang","year":"2024","unstructured":"Huang, S., Dong, L., Wang, W.: Language is not all you need: aligning perception with language models. Adv. Neural. Inf. Process. Syst. 36, 1\u201311 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"359_CR61","doi-asserted-by":"publisher","unstructured":"Gong, T., Lyu, C., Zhang, S.: Multimodal-gpt: a vision and language model for dialogue with humans\u201d ArXiv. (2023) https:\/\/doi.org\/10.48550\/arXiv.2305.04790.","DOI":"10.48550\/arXiv.2305.04790"},{"key":"359_CR62","doi-asserted-by":"publisher","unstructured":"Wei, T., Zhao, L., Zhang, L.: Skywork: a more open bilingual foundation model\u201d ArXiv. (2023) https:\/\/doi.org\/10.48550\/arXiv.2310.19341.","DOI":"10.48550\/arXiv.2310.19341"},{"key":"359_CR63","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205, (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"359_CR64","unstructured":"Bengio, Y., Ducharme, R., Vincent, P.: A neural probabilistic language model. Advances in neural information processing systems, vol. 13, (2000)"},{"key":"359_CR65","doi-asserted-by":"crossref","unstructured":"Schwenk, H., D\u00b4echelotte, D., Gauvain, J.-L.: Continuous space language models for statistical machine translation. In: Proceedings of the COLING\/ACL 2006 Main Conference Poster Sessions, pp. 723\u2013730, (2006)","DOI":"10.3115\/1273073.1273166"},{"key":"359_CR66","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Deoras, A., Povey, D., Burget, L., Cernock, J.: Strategies for training large scale neural network language models. In: 2011 IEEE Workshop on Automatic Speech Recognition & Understanding. IEEE, pp. 196\u2013201, (2011)","DOI":"10.1109\/ASRU.2011.6163930"},{"key":"359_CR67","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merrienboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: Encoder-decoder ap proaches,\u201d arXiv preprint arXiv:1409.1259, (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"359_CR68","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding,\u201d arXiv preprint arXiv:1810.04805, (2018)"},{"key":"359_CR69","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., Stoyanov, V. , Roberta: a robustly optimized bert pretraining approach,\u201d arXiv preprint arXiv:1907.11692, (2019)"},{"key":"359_CR70","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: Albert: a lite bert for self-supervised learning of language representations, arXiv preprint arXiv:1909.11942, (2019)"},{"key":"359_CR71","unstructured":"Clark, K., Luong, M.-T., Le, Q. V., Manning, C. D.: Electra: pre-training text encoders as discriminators rather than generators,\u201d arXiv preprint arXiv:2003.10555, (2020)"},{"key":"359_CR72","unstructured":"Lample G., Conneau, A.: Cross-lingual language model pretraining,\u201d arXiv preprint arXiv:1901.07291, (2019)"},{"key":"359_CR73","first-page":"1","volume":"32","author":"Z Yang","year":"2019","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q.V.: Xlnet: generalized autoregressive pretraining for language understanding. Adv. Neural. Inf. Process. Syst. 32, 1\u201329 (2019)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"359_CR74","first-page":"1","volume":"32","author":"L Dong","year":"2019","unstructured":"Dong, L., Yang, N., Wang, W., Wei, F., Liu, X., Wang, Y., Gao, J., Zhou, M., Hon, H.-W.: Unified language model pre-training for natural language understanding and generation. Adv. Neural. Inf. Process. Syst. 32, 1\u201323 (2019)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"359_CR75","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training, pp. 1\u201322, (2018)"},{"issue":"8","key":"359_CR76","first-page":"1","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 1\u201319 (2019)","journal-title":"OpenAI blog"},{"issue":"1","key":"359_CR77","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., Liu, P.J.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"359_CR78","doi-asserted-by":"crossref","unstructured":"Xue, L., Constant, N., Roberts, A., Kale, M., Al-Rfou, R., Siddhant, A., Barua, A., Raffel, C.: mt5: a massively multilingual pre-trained text-to-text transformer,\u201d arXiv preprint arXiv:2010.11934, (2020)","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"359_CR79","unstructured":"Song, K., Tan, X., Qin, T., Lu, J., Liu, T.-Y.: Mass: masked sequence to sequence pre-training for language generation,\u201d arXiv preprint arXiv:1905.02450, (2019)"},{"key":"359_CR80","doi-asserted-by":"crossref","unstructured":"Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., Zettlemoyer, L.: Bart: denoising sequence-to sequence pre-training for natural language generation, translation, and comprehension, arXiv preprint arXiv:1910.13461, (2019)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"359_CR81","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A.: Language models are few-shot learners. Advances in neural information processing systems, vol. 33, pp. 1877\u20131901, (2020)"},{"key":"359_CR82","unstructured":"Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H.P.D.O., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., Ray, A.: Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374, (2021)"},{"key":"359_CR83","unstructured":"Nakano, R., Hilton, J., Balaji, S., Wu, J., Ouyang, L., Kim, C., Hesse, C., Jain, S., Kosaraju, V., Saunders, W.: Webgpt: browser assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332, (2021)"},{"key":"359_CR84","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"359_CR85","unstructured":"OpenAI, \u201cGPT-4 Technical Report,\u201d https:\/\/arxiv.org\/pdf\/2303. 08774v3.pdf, (2023)"},{"key":"359_CR86","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozi` ere, B., Goyal N., Hambro, E., Azhar, F.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971, (2023)"},{"key":"359_CR87","unstructured":"Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S.: Llama 2: open foundation and fine-tuned chat models, arXiv preprint arXiv:2307.09288, (2023)"},{"key":"359_CR88","unstructured":"Taori, R., Gulrajani, I., Zhang, T., Dubois, Y., Li, X., Guestrin, C., Liang, P., Hashimoto, T. B.: Alpaca: a strong, replicable instruction following model, Stanford Center for Research on Foundation Models. https:\/\/crfm.stanford.edu\/2023\/03\/13\/alpaca.html, vol. 3 (6), pp. 1\u20137, (2023)"},{"key":"359_CR89","unstructured":"Dettmers, T., Pagnoni, A., Holtzman, A., Zettlemoyer, L.: Qlora: ef f icient finetuning of quantized llms, arXiv preprint arXiv:2305.14314, (2023)"},{"key":"359_CR90","unstructured":"Geng, X., Gudibande, A., Liu, H., Wallace, E., Abbeel, P., Levine, S., Song, D.: Koala: a dialogue model for academic research, Blog post, vol. 1, pp. 1\u201319, (2023)"},{"key":"359_CR91","unstructured":"Jiang, A.Q., Sablayrolles, A., Mensch, A., Bamford, C., Chaplot, D.S., Casas, D., Bressand, F., Lengyel, G., Lample, G., Saulnier, L.: \u201cMistral 7b,\u201d arXiv preprint arXiv:2310.06825, (2023)"},{"key":"359_CR92","unstructured":"Patil, S.G., Zhang, T., Wang, X., Gonzalez, J.E.: Gorilla: large language model connected with massive apis, (2023)"},{"key":"359_CR93","unstructured":"Pal, A., Karkhanis, D., Roberts, M., Dooley, S., Sundararajan, A., Naidu, S.: Giraffe: adventures in expanding context lengths in llms, arXiv preprint arXiv:2308.10882, (2023)"},{"key":"359_CR94","unstructured":"Wang, Y., Ivison, H., Dasigi, P., Hessel, J., Khot, T., Chandu, K., Wadden, D., MacMillan, K., Smith, N.A., Beltagy, I.: How far can camels go? exploring the state of instruction tuning on open resources, arXiv preprint arXiv:2306.04751, (2023)"},{"key":"359_CR95","unstructured":"Mahan, D., Carlow, R., Castricato, L., Cooper, N., Laforte.: Available: \u201cstable beluga models. [Online]. (https:\/\/huggingface.co\/stabilityai\/StableBeluga2)"},{"key":"359_CR96","unstructured":"Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H.W., Sutton, C., Gehrmann, S.: Palm: scaling language modeling with pathways, arXiv preprint arXiv:2204.02311, (2022)"},{"key":"359_CR97","unstructured":"Chung, H.W., Hou, L., Longpre, S., Zoph, B., Tay, Y., Fedus, W., Li, Y., Wang, X., Dehghani, M., Brahma, S.: Scaling instruction f inetuned language models, arXiv preprint arXiv:2210.11416, (2022)"},{"key":"359_CR98","unstructured":"Anil, R., Dai, A.M., Firat, O., Johnson, M., Lepikhin, D., Passos, A., Shakeri, S., Taropa, E., Bailey, P., Chen, Z.: Palm 2 technical report, arXiv preprint arXiv:2305.10403, (2023)"},{"key":"359_CR99","unstructured":"Singhal, K., Azizi, S., Tu, T., Mahdavi, S.S., Wei, J., Chung, H.W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., Payne, P.: Large language models encode clinical knowledge, arXiv preprint arXiv:2212.13138, (2022)"},{"key":"359_CR100","unstructured":"Zeng, W., Ren, X., Su, T., Wang, H., Liao, Y., Wang, Z., Jiang, X., Yang, Z., Wang, K., Zhang, X.: Pangu-\u03b1 : large-scale autoregressive pretrained chinese language models with auto-parallel computation, arXiv preprint arXiv:2104.12369, (2021)"},{"key":"359_CR101","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1016\/j.aiopen.2021.12.003","volume":"2","author":"Z Zhang","year":"2021","unstructured":"Zhang, Z., Gu, Y., Han, X., Chen, S., Xiao, C., Sun, Z., Yao, Y., Qi, F., Guan, J., Ke, P.: Cpm-2: large-scale, cost-effective pre-trained language models. AI Open 2, 216\u2013224 (2021)","journal-title":"AI Open"},{"key":"359_CR102","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.aiopen.2021.06.001","volume":"2","author":"S Yuan","year":"2021","unstructured":"Yuan, S., Zhao, H., Du, Z., Ding, M., Liu, X., Cen, Y., Zou, X., Yang, Z., Tang, J.: Wudaocorpora: a super large-scale chinese corpora for pre-training language models. AI Open 2, 65\u201368 (2021)","journal-title":"AI Open"},{"key":"359_CR103","unstructured":"Sun, Y., Wang, S., Feng, S., Ding, S., Pang, C., Shang, J., Liu, J., Chen, X., Zhao, Y., Lu, Y.: Ernie 3.0: Large-scale knowledge enhanced pre-training for language understanding and generation,\u201d arXiv preprint arXiv:2107.02137, (2021). 9, 22"},{"key":"359_CR104","unstructured":"Lieber, O., Sharir, O., Lenz, B., Shoham, Y.: Jurassic-1: technical details and evaluation, White Paper. AI21 Labs, vol. 1, pp. 1\u201332, (2021)"},{"key":"359_CR105","doi-asserted-by":"crossref","unstructured":"Kim, B., Kim, H., Lee, S.-W., Lee, G., Kwak, D., Jeon, D. H., Park, S., Kim, S., Kim, S., Seo D.: What changes can large-scale language models bring? intensive study on hyperclova: Billions-scale korean generative pretrained transformers, arXiv preprint arXiv:2109.04650, (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.274"},{"key":"359_CR106","unstructured":"Wu, S., Zhao, X., Yu, T., Zhang, R., Shen, C., Liu, H., Li, F., Zhu, H., Luo, J., Xu, L.: Yuan 1.0: large-scale pre-trained language model in zero-shot and few-shot learning, arXiv preprint arXiv:2110.04725, (2021)"},{"key":"359_CR107","unstructured":"Rae, J.W., Borgeaud, S., Cai, T., Millican, K., Hoffmann, J., Song, F., Aslanides, J., Henderson, S., Ring, R., Young, S.: Scaling language models: methods, analysis and insights from training gopher, arXiv preprint arXiv:2112.11446, (2021)"},{"key":"359_CR108","unstructured":"Wang, S., Sun, Y., Xiang, Y., Wu, Z., Ding, S., Gong, W., Feng, S., Shang, J., Zhao, Y., Pang, C. and Liu, J.: Ernie 3.0 titan: exploring larger scale knowledge enhanced pre-training for language understanding and generation, arXiv preprint arXiv:2112.12731, (2021)"},{"key":"359_CR109","doi-asserted-by":"crossref","unstructured":"Black, S., Biderman, S., Hallahan, E., Anthony, Q., Gao, L., Golding, L., He, H., Leahy, C., McDonell, K., Phang, J.: Gpt-neox 20b: an open-source autoregressive language model, arXiv preprint arXiv:2204.06745, (2022)","DOI":"10.18653\/v1\/2022.bigscience-1.9"},{"key":"359_CR110","unstructured":"Zhang, S., Roller, S., Goyal, N., Artetxe, M., Chen, M., Chen, S., Dewan, C., Diab, M., Li, X., Lin, X.V., Mihaylov, T.: Opt: open pre-trained transformer language models, arXiv preprint arXiv:2205.01068, (2022)"},{"key":"359_CR111","unstructured":"Le Scao, T., Fan, A., Akiki, C., Pavlick, E., Ili\u0107, S., Hesslow, D., Castagn\u00e9, R., Luccioni, A.S., Yvon, F., Gall\u00e9, M., Tow, J.: Bloom: a 176b parameter open-access multilingual language model, arXiv preprint arXiv:2211.05100, (2022)"},{"key":"359_CR112","doi-asserted-by":"publisher","first-page":"100026","DOI":"10.1016\/j.glmedi.2023.100026","volume":"1","author":"S Banerjee","year":"2023","unstructured":"Banerjee, S., Dunn, P., Conard, S., Ng, R.: Large language modeling and classical AI methods for the future of healthcare. J. Med., Surg. Public Health 1, 100026 (2023)","journal-title":"J. Med., Surg. Public Health"},{"key":"359_CR113","unstructured":"Du, N., Huang, Y., Dai, A.M., Tong, S., Lepikhin, D., Xu, Y., Krikun, M., Zhou, Y., Yu, A.W., Firat, O.: Glam: efficient scaling of language models with mixture-of-experts, In: International Conference on Machine Learning. PMLR, pp: 5547\u20135569, (2022)"},{"key":"359_CR114","unstructured":"Smith, S., Patwary, M., Norick, B., LeGresley, P., Rajbhandari, S., Casper, J., Liu, Z., Prabhumoye, S., Zerveas, G., Korthikanti, V.: Using deep speed and megatron to train megatron-turning nlg 530b, a large scale generative language model, arXiv preprint arXiv:2201.11990, (2022)"},{"key":"359_CR115","unstructured":"Hoffmann, J., Borgeaud, S., Mensch, A., Buchatskaya, E., Cai, T., Rutherford, E., Casas, D.D.L., Hendricks, L.A., Welbl, J., Clark, A.: Training compute-optimal large language models, arXiv preprint arXiv:2203.15556, (2022)"},{"key":"359_CR116","unstructured":"Soltan, S., Ananthakrishnan, S., FitzGerald, J., Gupta, R., Hamza, W., Khan, H., Peris, C., Rawls, S., Rosenbaum, A., Rumshisky, A.: Alexatm 20b: Few-shot learning using a large-scale multilingual seq2seq model, arXiv preprint arXiv:2208.01448, (2022)"},{"key":"359_CR117","unstructured":"Tay, Y., Dehghani, M., Tran, V.Q., Garcia, X., Wei, J., Wang, X., Chung, H.W., Shakeri, S., Bahri, D., Schuster, T., Zheng, H.S. Ul2: unifying language learning paradigms. In: The Eleventh International Conference on Learning Representations, (2022)"},{"key":"359_CR118","unstructured":"Zeng, A., Liu, X., Du, Z., Wang, Z., Lai, H., Ding, M., Yang, Z., Xu, Y., Zheng, W., Xia, X.: Glm-130b: An open bilingual pre-trained model, arXiv preprint arXiv:2210.02414, (2022)"},{"key":"359_CR119","unstructured":"Ren, X., Zhou, P., Meng, X., Huang, X., Wang, Y., Wang, W., Li, P., Zhang, X., Podolskiy, A., Arshinov, G.: Pangu-Towards trillion parameter language model with sparse heterogeneous computing, arXiv preprint arXiv:2303.10845, (2023)"},{"key":"359_CR120","unstructured":"Nijkamp, E., Pang, B., Hayashi, H., Tu, L., Wang, H., Zhou, Y., Savarese, S., Xiong, C.: Codegen: an open large language model for code with multi-turn program synthesis, arXiv preprint arXiv:2203.13474, (2022)"},{"key":"359_CR121","unstructured":"Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H.P.D.O., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman.: Evaluating large language models trained on code, arXiv preprint arXiv:2107.03374, (2021)"},{"issue":"6624","key":"359_CR122","doi-asserted-by":"publisher","first-page":"1092","DOI":"10.1126\/science.abq1158","volume":"378","author":"Y Li","year":"2022","unstructured":"Li, Y., Choi, D., Chung, J., Kushman, N., Schrittwieser, J., Leblond, R., Eccles, T., Keeling, J., Gimeno, F., Dal Lago, A.: Competition level code generation with alpha code. Science 378(6624), 1092\u20131097 (2022)","journal-title":"Science"},{"key":"359_CR123","unstructured":"Pang, R.Y., He, H.: Text generation by learning from demonstrations, arXiv preprint arXiv:2009.07839, (2020)"},{"key":"359_CR124","doi-asserted-by":"crossref","unstructured":"Wang, Y., Le, H., Gotmare, A.D., Bui, N.D., Li, J., Hoi, S.C.: Codet5+: open code large language models for code understanding and generation, arXiv preprint arXiv:2305.07922, (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.68"},{"key":"359_CR125","unstructured":"Li, R., Allal, L.B., Zi, Y., Muennighoff, N., Kocetkov, D., Mou, C., Marone, M., Akiki, C., Li, J., Chim, J.: Starcoder: may the source be with you!\u201d arXiv preprint arXiv:2305.06161, (2023)"},{"key":"359_CR126","unstructured":"Taylor, R., Kardas, M., Cucurull, G., Scialom, T., Hartshorn, A., Saravia, E., Poulton, A., Kerkez, V. and Stojnic, R., Galactica: a large language model for science, arXiv preprint arXiv:2211.09085, (2022)"},{"key":"359_CR127","unstructured":"Thoppilan, R., De Freitas, D., Hall, J., Shazeer, N., Kulshreshtha, A., Cheng, H.T., Jin, A., Bos, T., Baker, L., Du, Y., Li, Y.: Lamda: language models for dialog applications, arXiv preprint arXiv:2201.08239, (2022)"},{"key":"359_CR128","unstructured":"Wu, S., Irsoy, O., Lu, S., Dabravolski, V., Dredze, M., Gehrmann, S., Kambadur, P., Rosenberg, D., Mann, G.: Bloomberggpt: a large language model for finance. arXiv preprint arXiv:2303.17564, (2023)"},{"key":"359_CR129","doi-asserted-by":"crossref","unstructured":"Zhang, X., Yang, Q.: Xuanyuan 2.0: a large Chinese financial chat model with hundreds of billions parameters. arXiv preprint arXiv:2305.12002, (2023)","DOI":"10.1145\/3583780.3615285"},{"key":"359_CR130","unstructured":"Wei, J., Bosma, M., Zhao, V.Y., Guu, K., Yu, A.W., Lester, B., Du, N., Dai, A.M., Le, Q.V.: Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652, (2021)"},{"key":"359_CR131","unstructured":"Sanh, V., Webson, A., Raffel, C., Bach, S.H., Sutawika, L., Alyafeai, Z., Chaffin, A., Stiegler, A., Scao, T.L., Raja, A., Dey, M.: Multi-task prompted training enables zero-shot task generalization. arXiv preprint arXiv:2110.08207, (2021)"},{"key":"359_CR132","unstructured":"Borgeaud, S., Mensch, A., Hoffmann, J., Cai, T., Rutherford, E., Millican, K., Van Den Driessche, G.B., Lespiau, J.B., Damoc, B., Clark, A.: Improving language models by retrieving from trillions of tokens. In: International Conference on Machine Learning. PMLR, pp. 2206\u20132240, (2022)"},{"key":"359_CR133","unstructured":"Glaese, A., McAleese, N., Tr\u0119bacz, M., Aslanides, J., Firoiu, V., Ewalds, T., Rauh, M., Weidinger, L., Chadwick, M., Thacker, P., Campbell-Gillingham, L.: Improving alignment of dialogue agents via targeted human judgments. arXiv preprint arXiv:2209.14375, (2022)"},{"key":"359_CR134","first-page":"3843","volume":"35","author":"A Lewkowycz","year":"2022","unstructured":"Lewkowycz, A., Andreassen, A., Dohan, D., Dyer, E., Michalewski, H., Ramasesh, V., Slone, A., Anil, C., Schlag, I., Gutman-Solo, T.: Solving quantitative reasoning problems with language models. Adv. Neural. Inf. Process. Syst. 35, 3843\u20133857 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"359_CR135","unstructured":"Tay, Y., Dehghani, M., Tran, V.Q., Garcia, X., Wei, J., Wang, X., Chung, H.W., Shakeri, S., Bahri, D., Schuster, T., Zheng, H.S., N. Houlsby., D. Metzler.: Unifying language learning paradigms. arXiv preprint arXiv:2205.05131, (2022)"},{"key":"359_CR136","unstructured":"Biderman, S., Schoelkopf, H., Anthony, Q.G., Bradley, H., O\u2019Brien, K., Hallahan, E., Khan, M.A., Purohit, S., Prashanth, U.S., Raff, E. and Skowron, A.: Pythia: a suite for analyzing large language models across training and scaling. In: International Conference on Machine Learning. PMLR, pp. 2397\u20132430, (2023)"},{"key":"359_CR137","unstructured":"Mukherjee, S., Mitra, A., Jawahar, G., Agarwal, S., Palangi, H. and Awadallah, A.: Orca: progressive learning from complex explanation traces of gpt-4. arXiv preprint arXiv:2306.02707, (2023)"},{"key":"359_CR138","unstructured":"Huang, S., Dong, L., Wang, W., Hao, Y., Singhal, S., Ma, S., Lv, T., Cui, L., Mohammed, O.K., Patra, B. and Liu, Q.: Language is not all you need: Aligning perception with language models. arXiv preprint arXiv:2302.14045, (2023)"},{"key":"359_CR139","unstructured":"Team, G., Anil, R., Borgeaud, S., Alayrac, J.B., Yu, J., Soricut, R., Schalkwyk, J., Dai, A.M., Hauth, A., Millican, K. and Silver, D.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805, (2023)"},{"issue":"05","key":"359_CR140","first-page":"8878","volume":"34","author":"H Song","year":"2020","unstructured":"Song, H., Zhang, W.-N., Hu, J., Liu, T.: Generating persona consistent dialogues by exploiting natural language inference. Proc. AAAI Conf. Artif. Intell. 34(05), 8878\u20138885 (2020)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"issue":"6","key":"359_CR141","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s42256-023-00669-7","volume":"5","author":"F Stella","year":"2023","unstructured":"Stella, F., Della Santina, C., Hughes, J.: How can llms transform the robotic design process? Nat. Mach. Intell. 5(6), 1\u20134 (2023)","journal-title":"Nat. Mach. Intell."},{"key":"359_CR142","doi-asserted-by":"crossref","unstructured":"Niranjan, P.Y., Rajpurohit, V.S. and Malgi, R.: A survey on chat-bot system for agriculture domain. In: 2019 1st International Conference on Advances in Information Technology (ICAIT), pp. 99\u2013103, (2019)","DOI":"10.1109\/ICAIT47043.2019.8987429"},{"key":"359_CR143","doi-asserted-by":"crossref","unstructured":"Wolfram, S.: Alpha as the way to bring computational knowledge superpowers to chatgpt. Stephen Wolfram Writings RSS, Stephen Wolfram, LLC, vol. 9, pp. 1\u201314, (2023)","DOI":"10.31855\/0804a866-398"},{"key":"359_CR144","doi-asserted-by":"publisher","unstructured":"G. Lu, S. Li, and G. Mai, \u201cAgi for agriculture\u201d ArXiv. 2023. https:\/\/doi.org\/10.48550\/arXiv.2304.06136.","DOI":"10.48550\/arXiv.2304.06136"},{"key":"359_CR145","doi-asserted-by":"publisher","unstructured":"Peng, R., Liu, K., Yang, P.: Embedding-based retrieval with llm for effective agriculture information extracting. from https:\/\/doi.org\/10.48550\/arXiv.2308.03107. unstructured data. ArXiv. (2023)","DOI":"10.48550\/arXiv.2308.03107"},{"key":"359_CR146","unstructured":"Qi, C.R., Su, H., Mo, K. and Guibas, L.J.: Pointnet: deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652\u2013660, (2017)"},{"key":"359_CR147","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695, (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"359_CR148","doi-asserted-by":"publisher","unstructured":"Zhu, H., Qin, S., Su, M., Lin, C., Li, A. and Gao, J.: Harnessing large vision and language models in agriculture: a review, pp. 1\u201354, https:\/\/doi.org\/10.48550\/arXiv.2403.11858","DOI":"10.48550\/arXiv.2403.11858"},{"key":"359_CR149","doi-asserted-by":"publisher","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A.: Hierarchical text-conditional image generation with clip latent. ArXiv. (2022), 1(2):3. https:\/\/doi.org\/10.48550\/arXiv.2204.06125","DOI":"10.48550\/arXiv.2204.06125"},{"key":"359_CR150","first-page":"1","volume":"36","author":"Y Shen","year":"2024","unstructured":"Shen, Y., Song, K., Tan, X.: Hugginggpt: solving ai tasks with chatgpt and its friends in hugging face. Adv. Neural. Inf. Process. Syst. 36, 1\u201325 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"359_CR151","unstructured":"Radford, A., Kim, J.W., Xu, T.: Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning, pp. 28492\u201328518, (2023)"},{"key":"359_CR152","first-page":"1","volume":"32","author":"Y Ren","year":"2019","unstructured":"Ren, Y., Ruan, Y., Tan, X.: Fastspeech: fast, robust and controllable text to speech. Adv. Neural. Inf. Process. Syst. 32, 1\u201335 (2019)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"359_CR153","first-page":"276","volume":"6","author":"N Kundu","year":"2022","unstructured":"Kundu, N., Rani, G., Dhaka, V.S., Gupta, K., Nayaka, S.C., Vocaturo, E., Zumpano, E.: Disease detection, severity prediction, and crop loss estimation in MaizeCrop using deep learning. Artif. Intell. Agric. 6, 276\u2013291 (2022)","journal-title":"Artif. Intell. Agric."},{"issue":"18","key":"359_CR154","doi-asserted-by":"publisher","first-page":"7877","DOI":"10.3390\/s23187877","volume":"23","author":"VS Dhaka","year":"2023","unstructured":"Dhaka, V.S., Kundu, N., Rani, G., Zumpano, E., Vocaturo, E.: Role of internet of things and deep learning techniques in plant disease detection and classification: a focused review. Sensors 23(18), 7877 (2023). https:\/\/doi.org\/10.3390\/s23187877","journal-title":"Sensors"},{"key":"359_CR155","doi-asserted-by":"publisher","first-page":"9483","DOI":"10.1109\/ACCESS.2022.3142848","volume":"10","author":"MS Farooq","year":"2022","unstructured":"Farooq, M.S., Sohail, O.O., Abid, A., Rasheed, S.: A survey on the role of iot in agriculture for the implementation of smart livestock environment. IEEE Access 10, 9483\u20139505 (2022)","journal-title":"IEEE Access"},{"key":"359_CR156","unstructured":"Yang, J., Gao, M., Li, Z., Gao, S., Wang, F., Zheng, F.: Track anything: segment anything meets videos. arXiv preprint arXiv:2304.11968, (2023)"},{"key":"359_CR157","unstructured":"Bommasani, R., Hudson, D.A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M.S., Bohg, J., Bosselut, A., Brunskill, E., Brynjolfsson, E.: On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258, (2021)"},{"key":"359_CR158","doi-asserted-by":"publisher","first-page":"62448","DOI":"10.1109\/ACCESS.2020.2981496","volume":"8","author":"H Li","year":"2020","unstructured":"Li, H., Tang, J.: Dairy goat image generation based on improved-self-attention generative adversarial networks. IEEE Access 8, 62448\u201362457 (2020)","journal-title":"IEEE Access"},{"key":"359_CR159","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/978-981-16-2709-5_2","volume-title":"Soft Computing for Problem Solving: Proceedings of SocProS 2020","author":"K Priyanka Singh","year":"2021","unstructured":"Priyanka Singh, K., Devi, J., Varish, N.: Muzzle pattern based cattle identification using generative adversarial networks. In: Tiwari, A., Ahuja, K., Yadav, A., Bansal, J.C., Deep, K., Nagar, A.K. (eds.) Soft Computing for Problem Solving: Proceedings of SocProS 2020, pp. 13\u201323. Springer Singapore, Singapore (2021). https:\/\/doi.org\/10.1007\/978-981-16-2709-5_2"},{"issue":"23","key":"359_CR160","doi-asserted-by":"publisher","first-page":"13396","DOI":"10.3390\/su132313396","volume":"13","author":"G Ahmed","year":"2021","unstructured":"Ahmed, G., Malick, R.A.S., Akhunzada, A., Zahid, S., Sagriand, M.R., Gani, A.: An approach towards iot-based predictive service for early detection of diseases in poultry chickens. Sustainability 13(23), 13396\u201314009 (2021)","journal-title":"Sustainability"},{"key":"359_CR161","doi-asserted-by":"publisher","first-page":"105087","DOI":"10.1016\/j.compag.2019.105087","volume":"167","author":"H Mal\u00f8y","year":"2019","unstructured":"Mal\u00f8y, H., Aamodt, A., Misimi, E.: A spatiotemporal recurrent network for salmon feeding action recognition from underwater videos in aquaculture. Comput. Electron. Agric. 167, 105087 (2019)","journal-title":"Comput. Electron. Agric."},{"issue":"2","key":"359_CR162","doi-asserted-by":"publisher","first-page":"699","DOI":"10.13031\/trans.12684","volume":"61","author":"J Zhao","year":"2018","unstructured":"Zhao, J., Li, Y., Zhang, F., Zhu, S., Liu, Y., Lu, H., Ye, Z.: Semi-supervised learning- based live fish identification in aquaculture using modified deep convolutional generative adversarial networks. Trans. ASABE 61(2), 699\u2013710 (2018)","journal-title":"Trans. ASABE"},{"key":"359_CR163","doi-asserted-by":"publisher","first-page":"104852","DOI":"10.1016\/j.compag.2019.104852","volume":"163","author":"H Gensheng","year":"2019","unstructured":"Gensheng, H., Haoyu, W., Zhang, Y., Wan, M.: A low shot learning method for tea leaf\u2019s disease identification. Comput. Electron. Agric. 163, 104852 (2019). https:\/\/doi.org\/10.1016\/j.compag.2019.104852","journal-title":"Comput. Electron. Agric."},{"key":"359_CR164","doi-asserted-by":"publisher","first-page":"106279","DOI":"10.1016\/j.compag.2021.106279","volume":"187","author":"A Abbas","year":"2021","unstructured":"Abbas, A., Jain, S., Gour, M., Vankudothu, S.: Tomato plant disease detection using transfer learning with CGAN synthetic images. Comput. Electron. Agric. 187, 106279 (2021)","journal-title":"Comput. Electron. Agric."},{"key":"359_CR165","doi-asserted-by":"publisher","first-page":"104967","DOI":"10.1016\/j.compag.2019.104967","volume":"165","author":"C Douarre","year":"2019","unstructured":"Douarre, C., Crispim-Junior, C.F., Gelibert, A., Tougne, L., Rousseau, D.: Novel data augmentation strategies to boost supervised segmentation of plant disease. Comput. Electron. Agric. 165, 104967 (2019)","journal-title":"Comput. Electron. Agric."},{"key":"359_CR166","doi-asserted-by":"publisher","first-page":"012093","DOI":"10.1088\/1742-6596\/1883\/1\/012093","volume":"1883","author":"M Zeng","year":"2021","unstructured":"Zeng, M., Gao, H., Wan, L.: Few-shot grape leaf diseases classification based on generative adversarial network. J. Phys. Conf. Ser. 1883, 012093 (2021)","journal-title":"J. Phys. Conf. Ser."},{"key":"359_CR167","doi-asserted-by":"publisher","DOI":"10.2196\/44293","volume":"2","author":"D Oniani","year":"2023","unstructured":"Oniani, D., Chandrasekar, P., Sivarajkumar, S.: Few-Shot learning for clinical natural language processing using siamese neural networks: algorithm development and validation study. JMIR AI. 2, e44293 (2023)","journal-title":"JMIR AI."},{"key":"359_CR168","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"359_CR169","doi-asserted-by":"publisher","first-page":"101706","DOI":"10.1016\/j.ecoinf.2022.101706","volume":"70","author":"J Pan","year":"2022","unstructured":"Pan, J., Xia, L., Wu, Q., Guo, Y., Chen, Y., Tian, X.: Automatic strawberry leaf scorch severity estimation via faster R-CNN and few-shot learning. Ecol. Inf. 70, 101706 (2022)","journal-title":"Ecol. Inf."},{"key":"359_CR170","doi-asserted-by":"crossref","unstructured":"Bai, Y., Geng, X., Mangalam, K.: Sequential modeling enables scalable learning for large vision models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 22861\u201322872, (2024)","DOI":"10.1109\/CVPR52733.2024.02157"},{"key":"359_CR171","unstructured":"Srivastava, N., Salakhutdinov, R.R.: Multimodal learning with deep boltzmann machines. Advances in neural information processing systems, vol. 25, (2012)"},{"issue":"22","key":"359_CR172","doi-asserted-by":"publisher","first-page":"3783","DOI":"10.3390\/rs12223783","volume":"12","author":"S Khanal","year":"2020","unstructured":"Khanal, S., Kc, K., Fulton, J.P.: Remote sensing in agriculture\u2014accomplishments, limitations, and opportunities. Remote. Sens. 12(22), 3783\u20133813 (2020)","journal-title":"Remote. Sens."},{"key":"359_CR173","first-page":"2663","volume":"2023","author":"J Wu","year":"2023","unstructured":"Wu, J., Hovakimyan, N., Hobbs, J.: Genco: an auxiliary generator from contrastive learning for enhanced few-shot learning in remote sensing. ECAI 2023, 2663\u20132671 (2023)","journal-title":"ECAI"},{"key":"359_CR174","doi-asserted-by":"publisher","unstructured":"Hong, D., Zhang, B., Li, X.: SpectralGPT: Spectral remote sensing foundation model. ArXiv. 2023. https:\/\/doi.org\/10.48550\/arXiv.2311.07113.","DOI":"10.48550\/arXiv.2311.07113"},{"issue":"2","key":"359_CR175","doi-asserted-by":"publisher","first-page":"354","DOI":"10.3390\/rs15020354","volume":"15","author":"E Omia","year":"2023","unstructured":"Omia, E., Bae, H., Park, E.: Remote sensing in field crop monitoring: a comprehensive review of sensor systems, data analyses and recent advances. Remote. Sens. 15(2), 354\u2013379 (2023)","journal-title":"Remote. Sens."},{"key":"359_CR176","doi-asserted-by":"publisher","unstructured":"Feng, X., Yu, Z., Fang, H.: Plantorgan hunter: a deep learning-based framework for quantitative profiling plant subcellular morphology. https:\/\/doi.org\/10.21203\/rs.3.rs-1811819\/v1, (2022)","DOI":"10.21203\/rs.3.rs-1811819\/v1"},{"key":"359_CR177","unstructured":"Yang, X., Dai, H., Wu, Z., Bist, R., Subedi, S., Sun, J., Lu, G., Li, C., Liu, T., Chai, L.: Samfor poultry science. arXiv preprint arXiv:2305.10254, (2023c)"},{"key":"359_CR178","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: exceeding yolo series in 2021\u201d arXiv preprint arXiv:2107.08430, (2021)"},{"key":"359_CR179","unstructured":"Yang, J., Gao, M., Li, Z., Gao, S., Wang, F., Zheng, F.: Track anything: Segment anything meets videos. arXiv preprint arXiv:2304.11968, (2023a)"},{"key":"359_CR180","doi-asserted-by":"crossref","unstructured":"Williams, D., Macfarlane, F., Britten, A.: Leaf only sam: a segment anything pipeline for zero-shot automated leaf segmentation. arXiv preprint arXiv:2305.09418, (2023a)","DOI":"10.1016\/j.atech.2024.100515"},{"key":"359_CR181","doi-asserted-by":"publisher","first-page":"132563","DOI":"10.1016\/j.jclepro.2022.132563","volume":"362","author":"L Yu","year":"2023","unstructured":"Yu, L., Liu, S., Wang, F.: Strategies for agricultural production management based on land, water and carbon footprints on the Qinghai-Tibet Plateau. J. Clean. Prod. 362, 132563 (2023)","journal-title":"J. Clean. Prod."},{"issue":"9","key":"359_CR182","doi-asserted-by":"publisher","first-page":"2672","DOI":"10.3390\/s20092672","volume":"20","author":"S Fountas","year":"2020","unstructured":"Fountas, S., Mylonas, N., Malounas, I., Rodias, E., Hellmann Santos, C., Pekkeriet, E.: Agricultural robotics for field operations. Sensors 20(9), 2672\u20132699 (2020)","journal-title":"Sensors"},{"key":"359_CR183","unstructured":"Team, A.A., Bauer, J., Baumli, K., Baveja, S., Behbahani, F., Bhoopchand, A., Bradley-Schmieg, N., Chang, M., Clay, N., Collister, A., Dasagi, V.: Human timescale adaptation in an open-ended task space. arXiv preprint arXiv:2301.07608, (2023)"},{"key":"359_CR184","doi-asserted-by":"crossref","unstructured":"Ganeshkumar, C., David, A., Sankar, J.G., Saginala, M.: Application of drone technology in agriculture: a predictive forecasting of pest and disease incidence. In: Applying Drone Technologies and Robotics for Agricultural Sustainability, pp. 50\u201381, (2023)","DOI":"10.4018\/978-1-6684-6413-7.ch004"},{"key":"359_CR185","doi-asserted-by":"publisher","unstructured":"Yang, X., Dai, H., Wu, Z.: Sam for poultry science. ArXiv. (2023) https:\/\/doi.org\/10.48550\/arXiv.2305.10254","DOI":"10.48550\/arXiv.2305.10254"},{"key":"359_CR186","doi-asserted-by":"publisher","unstructured":"Yang, J., Gao, M., Li, Z.: Track anything: segment anything meets videos. ArXiv. https:\/\/doi.org\/10.48550\/arXiv.2304.11968, (2023a)","DOI":"10.48550\/arXiv.2304.11968"},{"key":"359_CR187","doi-asserted-by":"crossref","unstructured":"Singh, I., Blukis, V., Mousavian, A., Goyal, A., Xu, D., Tremblay, J., Fox, D., Thomason, J., Garg, A.: Progprompt: generating situated robot task plans using large language models. In: 2023 IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp. 11523\u201311530, (2023)","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"359_CR188","unstructured":"Zhong, T., Wei, Y., Yang, L., Wu, Z., Liu, Z., Wei, X., Li, W., Yao, J., Ma, C., Li, X., Zhu, D.: Chatabl: abductive learning via natural language interaction with chatgpt. arXiv preprint arXiv:2304.11107, (2023)"},{"key":"359_CR189","doi-asserted-by":"crossref","unstructured":"Wu, J., Antonova, R., Kan, A., Lepert, M., Zeng, A., Song, S., Bohg, J., Rusinkiewicz, S., Funkhouser, T.: Tidybot: personalized robot assistance with large language models. arXiv preprint arXiv:2305.05658, (2023)","DOI":"10.1109\/IROS55552.2023.10341577"},{"key":"359_CR190","unstructured":"Driess, D., Xia, F., Sajjadi, M.S., Lynch, C., Chowdhery, A., Ichter, B., Wahid, A., Tompson, J., Vuong, Q., Yu, T. and Huang, W.: Palm-e: an embodied multimodal language model. arXiv preprint arXiv:2303.03378, (2023)"},{"key":"359_CR191","doi-asserted-by":"crossref","unstructured":"Zhang, B., Soh, H.: Large language models as zero-shot human models for human-robot interaction. arXiv preprint arXiv:2303.03548, (2023)","DOI":"10.1109\/IROS55552.2023.10341488"},{"key":"359_CR192","unstructured":"Huang, W., Xia, F., Xiao, T., Chan, H., Liang, J., Florence, P., Zeng, A., Tompson, J., Mordatch, I., Chebotar, Y. and Sermanet, P.: Inner monologue: embodied reasoning through planning with language models. in 6th Annual Conference on Robot Learning, 2022. [Online]. Available: https:\/\/openreview.net\/forum?id=3R3Pz5i0tye."},{"issue":"8","key":"359_CR193","doi-asserted-by":"publisher","first-page":"999","DOI":"10.1007\/s10514-023-10135-3","volume":"47","author":"I Singh","year":"2023","unstructured":"Singh, I., Blukis, V., Mousavian, A., Goyal, A., Xu, D., Tremblay, J., Fox, D., Thomason, J., Garg, A.: Progprompt: program generation for situated robot task planning using large language models. Auton. Robot. 47(8), 999\u20131012 (2023)","journal-title":"Auton. Robot."},{"key":"359_CR194","doi-asserted-by":"publisher","first-page":"1221739","DOI":"10.3389\/frobt.2023.1221739","volume":"10","author":"G Chalvatzaki","year":"2023","unstructured":"Chalvatzaki, G., Younes, A., Nandha, D., Le, A.T., Ribeiro, L.F., Gurevych, I.: Learning to reason over scene graphs: a case study of finetuning gpt-2 into a robot language model for grounded task planning. Front. Robot. AI 10, 1221739 (2023)","journal-title":"Front. Robot. AI"},{"key":"359_CR195","doi-asserted-by":"crossref","unstructured":"Huang, C., Mees, O., Zeng, A., Burgard, W.: Visual language maps for robot navigation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp. 10608\u201310615, (2023)","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"359_CR196","doi-asserted-by":"publisher","unstructured":"Chen, C., Du, Y., Fang, Z.:Model composition for multimodal large language models. ArXiv. (2024) https:\/\/doi.org\/10.48550\/arXiv.2402.12750","DOI":"10.48550\/arXiv.2402.12750"},{"key":"359_CR197","doi-asserted-by":"publisher","first-page":"107993","DOI":"10.1016\/j.compag.2023.107993","volume":"211","author":"Y Cao","year":"2023","unstructured":"Cao, Y., Chen, L., Yuan, Y., Sun, G.: Cucumber disease recognition with small samples using image-text-label-based multi-modal language model. Comput. Electron. Agric. 211, 107993 (2023)","journal-title":"Comput. Electron. Agric."},{"issue":"6","key":"359_CR198","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.3390\/agriculture13061238","volume":"13","author":"J Dhakshayani","year":"2023","unstructured":"Dhakshayani, J., Surendiran, B.: M2f-net: A deep learning-based multi-modal classification with high-throughput phenotyping for identification of overabundance of fertilizers. Agriculture 13(6), 1238\u20131271 (2023)","journal-title":"Agriculture"},{"issue":"1","key":"359_CR199","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1002\/rob.21877","volume":"37","author":"A Bender","year":"2020","unstructured":"Bender, A., Whelan, B., Sukkarieh, S.: A high-resolution, multimodal data set for agricultural robotics: a Ladybird\u2019s-eye view of Brassica. J. Field Robot. 37(1), 73\u201396 (2020)","journal-title":"J. Field Robot."},{"key":"359_CR200","doi-asserted-by":"publisher","first-page":"107993","DOI":"10.1016\/j.compag.2023.107993","volume":"211","author":"Y Cao","year":"2023","unstructured":"Cao, Y., Chen, L., Yuan, Y.: Cucumber disease recognition with small samples using image-text label-based multi-modal language model. Comput. Electron. Agric. 211, 107993 (2023)","journal-title":"Comput. Electron. Agric."},{"issue":"107208","key":"359_CR201","first-page":"1","volume":"200","author":"Y Lu","year":"2022","unstructured":"Lu, Y., Chen, D., Olaniyi, E., Huang, Y.: Generative adversarial networks (gans) for image augmentation in agriculture: a systematic review. Comput. Electron. Agric. 200(107208), 1\u201325 (2022)","journal-title":"Comput. Electron. Agric."},{"key":"359_CR202","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1016\/j.compag.2017.09.019","volume":"142","author":"Y Tao","year":"2017","unstructured":"Tao, Y., Zhou, J.: Automatic apple recognition based on the fusion of color and 3D feature for robotic fruit picking. Comput. Electron. Agric. 142, 388\u2013396 (2017)","journal-title":"Comput. Electron. Agric."},{"issue":"1","key":"359_CR203","first-page":"117","volume":"79","author":"A Gangwar","year":"2024","unstructured":"Gangwar, A., Dhaka, V.S., Rani, G., Khandelwal, S., Zumpano, E., Vocaturo, E.: Time and space efficient multi-model convolution vision transformer for tomato disease detection from leaf images with varied backgrounds. Comput. Mater. Contin. 79(1), 117\u2013142 (2024)","journal-title":"Comput. Mater. Contin."},{"issue":"3361","key":"359_CR204","first-page":"1","volume":"12","author":"M Xu","year":"2022","unstructured":"Xu, M., Yoon, S., Fuentes, A., Yang, J., Park, D.S.: Style-consistent image translation: a novel data augmentation paradigm to improve plant disease recognition. Front. Plant Sci. 12(3361), 1\u201326 (2022)","journal-title":"Front. Plant Sci."},{"issue":"11","key":"359_CR205","doi-asserted-by":"publisher","first-page":"11623","DOI":"10.1109\/TITS.2023.3285442","volume":"24","author":"D Chen","year":"2023","unstructured":"Chen, D., Hajidavalloo, M.R., Li, Z., Chen, K., Wang, Y., Jiang, L., Wang, Y.: Deep multi-agent reinforcement learning for highway on-ramp merging in mixed traffic. IEEE Trans. Intell. Transp. Syst. 24(11), 11623\u201311638 (2023). https:\/\/doi.org\/10.1109\/TITS.2023.3285442","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"359_CR206","first-page":"75","volume":"2022","author":"R Gandhi","year":"2022","unstructured":"Gandhi, R.: Deep reinforcement learning for agriculture: principles and use cases. Data Sci. Agric. Nat. Resour. Manag. 2022, 75\u201394 (2022)","journal-title":"Data Sci. Agric. Nat. Resour. Manag."},{"key":"359_CR207","doi-asserted-by":"crossref","unstructured":"Zhou, N.: Intelligent control of agricultural irrigation based on reinforcement learning,\u201d Journal of Physics: conference series. IOP Publishing, vol. 1601, pp. 1\u201311, (2020)","DOI":"10.1088\/1742-6596\/1601\/5\/052031"},{"key":"359_CR208","doi-asserted-by":"crossref","unstructured":"Hadi, M.U., Al Tashi, Q., Shah, A., Qureshi, R., Muneer, A., Irfan, M., Zafar, A., Shaikh, M.B., Akhtar, N., Wu, J., Mirjalili, S.: Large language models: a comprehensive survey of its applications, challenges, limitations, and future prospects. TechRxiv, (2023)","DOI":"10.36227\/techrxiv.23589741.v3"},{"key":"359_CR209","doi-asserted-by":"crossref","unstructured":"Dong, X.L., Moon, S., Xu, Y.E., Malik, K., Yu, Z.: Towards next-generation intelligent assistants leveraging llm techniques. In: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 5792\u20135793, (2023)","DOI":"10.1145\/3580305.3599572"},{"key":"359_CR210","unstructured":"Pandya, K., Holia, M.: Automating customer service using long-chain: building custom open-source gpt chatbot for organizations. arXiv preprint arXiv:2310.05421, (2023)"},{"key":"359_CR211","doi-asserted-by":"crossref","unstructured":"Rao, A., Kim, J., Kamineni, M., Pang, M., Lie, W., Succi, M.D.: Evaluating chatgpt as an adjunct for radiologic decision-making. medRxiv, pp. 1\u201320, (2023)","DOI":"10.1101\/2023.02.02.23285399"},{"issue":"11","key":"359_CR212","doi-asserted-by":"publisher","first-page":"e2343689","DOI":"10.1001\/jamanetworkopen.2023.43689","volume":"6","author":"M Benary","year":"2023","unstructured":"Benary, M., Wang, X.D., Schmidt, M., Soll, D., Hilfenhaus, G., Nassir, M., Sigler, C., Kn\u00f6dler, M., Keller, U., Beule, D.: Leveraging large language models for decision support in personalized oncology. JAMA Netw. Open 6(11), e2343689\u2013e2343689 (2023)","journal-title":"JAMA Netw. Open"},{"key":"359_CR213","doi-asserted-by":"crossref","unstructured":"Montagna, S., Ferretti, S., Klopfenstein, L.C., Florio, A., Pengo, M.F.: Data decentralization of llm-based chatbot systems in chronic disease self-management. In: Proceedings of the 2023 ACM Conference on Information Technology for Social Good, pp. 205\u2013212, (2023)","DOI":"10.1145\/3582515.3609536"},{"issue":"3","key":"359_CR214","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/s10439-023-03306-x","volume":"2","author":"S Pal","year":"2023","unstructured":"Pal, S., Bhattacharya, M., Lee, S.-S., Chakraborty, C.: A domain-specific next-generation large language model (llm) or chatgpt is required for biomedical engineering and research. Ann. Biomed. Eng. 2(3), 451\u2013454 (2023)","journal-title":"Ann. Biomed. Eng."},{"issue":"1","key":"359_CR215","doi-asserted-by":"publisher","first-page":"e48291","DOI":"10.2196\/48291","volume":"9","author":"A Abd-Alrazaq","year":"2023","unstructured":"Abd-Alrazaq, A., AlSaad, R., Alhuwail, D., Ahmed, A., Healy, P.M., Latifi, S., Aziz, S., Damseh, R., Alrazak, S.A., Sheikh, J.: Large language models in medical education: opportunities, challenges, and future directions. JMIR Med. Educ. 9(1), e48291 (2023)","journal-title":"JMIR Med. Educ."},{"key":"359_CR216","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2023.1166120","author":"L De Angelis","year":"2023","unstructured":"De Angelis, L., Baglivo, F., Arzilli, G., Privitera, G.P., Ferragina, P., Tozzi, A.E., Rizzo, C.: Chatgpt and the rise of large language models: the new ai-driven infodemic threat in public health. Front. Public Health (2023). https:\/\/doi.org\/10.3389\/fpubh.2023.1166120","journal-title":"Front. Public Health"},{"key":"359_CR217","doi-asserted-by":"publisher","first-page":"102274","DOI":"10.1016\/j.lindif.2023.102274","volume":"103","author":"E Kasneci","year":"2023","unstructured":"Kasneci, E., Se\u00dfler, K., K\u00fcchemann, S., Bannert, M., Dementieva, D., Fischer, F., Gasser, U., Groh, G., G\u00fcnnemann, S., Hullermeier, E.: Chatgpt for good? on opportunities and challenges of large language models for education. Learn. Individ. Differ. 103, 102274 (2023)","journal-title":"Learn. Individ. Differ."},{"issue":"6","key":"359_CR218","first-page":"1","volume":"14","author":"JC Young","year":"2023","unstructured":"Young, J.C., Shishido, M.: Investigating openai\u2019s chatgpt potentials in generating chatbot\u2019s dialogue for English as a foreign language learning. Int. J. Adv. Comput. Sci. Appl. 14(6), 1\u201328 (2023)","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"359_CR219","doi-asserted-by":"crossref","unstructured":"Altm\u00e4e, S., Sola-Leyva, A., Salumets, A.: Artificial intelligence in scientific writing: a friend or a foe?. Reproductive BioMedicine Online, (2023)","DOI":"10.1016\/j.rbmo.2023.04.009"},{"key":"359_CR220","unstructured":"Yang, K., Swope, A., Gu, A., Chalamala, R., Song, P., Yu, S., Godil, S., Prenger, R.J., Anandkumar, A.: Leandojo: theorem proving with retrieval-augmented language models. arXiv preprint arXiv:2306.15626, (2023)"},{"key":"359_CR221","first-page":"1","volume":"100017","author":"Y Liu","year":"2023","unstructured":"Liu, Y., Han, T., Ma, S., Zhang, J., Yang, Y., Tian, J., He, H., Li, A., He, M., Liu, Z.: Summary of ChatGPT-related research and perspective towards the future of large language models. Meta-Radiol. 100017, 1\u201321 (2023)","journal-title":"Meta-Radiol."},{"key":"359_CR222","doi-asserted-by":"crossref","unstructured":"Guha, N., Nyarko, J., Ho, D., R\u00e9, C., Chilton, A., Chohlas-Wood, A., Peters, A., Waldon, B., Rockmore, D., Zambrano, D., Talisman, D.: Legalbench: a collaboratively built benchmark for measuring legal reasoning in large language models. arXiv preprint arXiv:2308.11462, (2023)","DOI":"10.2139\/ssrn.4583531"},{"key":"359_CR223","doi-asserted-by":"crossref","unstructured":"Yang, H., Liu, X.Y., Wang, C.D.: Fingpt: open-source financial large language models. arXiv preprint arXiv:2306.06031, (2023)","DOI":"10.2139\/ssrn.4489826"},{"key":"359_CR224","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, S., Ding, H., Chen, H.: Large language models in finance: a survey. In: Proceedings of the Fourth ACM International Conference on AI in Finance, pp. 374\u2013382, (2023)","DOI":"10.1145\/3604237.3626869"},{"key":"359_CR225","first-page":"452","volume":"7","author":"T Kwiatkowski","year":"2019","unstructured":"Kwiatkowski, T., Palomaki, J., Redfield, O., Collins, M., Parikh, A., Alberti, C., Epstein, D., Polosukhin, I., Devlin, J., Lee, K., Toutanova, K., Jones, L., Kelcey, M., Chang, M.-W., Dai, A.M., Uszkoreit, J., Le, Q., Petrov, S.: Natural questions: a benchmark for question answering research. Trans. Assoc. Comput. Linguist. 7, 452\u2013466 (2019)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"359_CR226","unstructured":"Hendrycks, D., Burns, C., Basart, S., Zou, A., Mazeika, M., Song, D., Steinhardt, J.: Measuring massive multitask language understanding. In: Proceedings of 9th International Conference on Learning Representations\u00a0(ICLR), Vienna, Austria, pp. 1\u201327, (2021)"},{"key":"359_CR227","unstructured":"Austin, J., Odena, A., Nye, M., Bosma, M., Michalewski, H., Dohan, D., Jiang, E., Cai, C., Terry, M., & Le, Q.: Program synthesis with large language models. arXiv preprint arXiv:2108.07732, (2021)"},{"key":"359_CR228","doi-asserted-by":"crossref","unstructured":"Choi, E., He, H., Iyyer, M., Yatskar, M., Yih, W.T., Choi, Y., Liang, P. & Zettlemoyer, L.: QuAC: Question answering in context, In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, pp. 2174\u20132184, (2018)","DOI":"10.18653\/v1\/D18-1241"},{"key":"359_CR229","unstructured":"Hendrycks, D., Basart, S., Kadavath, S., Mazeika, M., Arora, A., Guo, E., Burns, C., Puranik, S., He, H., Song, D. & Steinhardt, J.: Measuring coding challenge competence with apps. https:\/\/arxiv.org\/abs\/2105.09938, (2021)"},{"key":"359_CR230","unstructured":"Zhong, V., Xiong, C., Socher, R.: Seq2sql: generating structured queries from a natural language using reinforcement learning. arXiv preprint arXiv:1709.00103, (2017)"},{"key":"359_CR231","doi-asserted-by":"crossref","unstructured":"Joshi, M., Choi, E., Weld, D.S., Zettlemoyer, L.: TriviaQA: a large scale distantly supervised challenge dataset for reading comprehension. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, vol. 1, pp. 1601\u20131611, (2017)","DOI":"10.18653\/v1\/P17-1147"},{"key":"359_CR232","doi-asserted-by":"crossref","unstructured":"Lai, G., Xie, Q., Liu, H., Yang, Y., Hovy, E.: RACE: large-scale reading comprehension dataset from examinations. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 785\u2013794, (2017)","DOI":"10.18653\/v1\/D17-1082"},{"key":"359_CR233","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev K., Liang P.: SQuAD: 100,000+ questions for machine comprehension of text. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, pp: 2383\u20132392, (2016)","DOI":"10.18653\/v1\/D16-1264"},{"key":"359_CR234","unstructured":"Clark, C., Lee, K., Chang, M.W., Kwiatkowski, T., Collins, M., Toutanova, K.: Boolq: exploring the surprising difficulty of natural yes\/no questions. CoRR, vol: abs\/1905.10044, (2019)"},{"key":"359_CR235","doi-asserted-by":"crossref","unstructured":"Khashabi, D., Chaturvedi, S., Roth, M., Upadhyay, S.,Roth, D.: Looking beyond the surface: a challenge set for reading comprehension over multiple sentences. In: Proceedings of North American Chapter of the Association for Computational Linguistics (NAACL), (2018)","DOI":"10.18653\/v1\/N18-1023"},{"key":"359_CR236","unstructured":"Cobbe, K., Kosaraju, V., Bavarian, M., Chen, M., Jun, H., Kaiser, L., Plappert, M., Tworek, J., Hilton, J., Nakano, R., Hesse, C.: Training verifiers to solve math word problems. CoRR, vol. abs\/2110.14168, Available: https: \/\/arxiv.org\/abs\/2110.14168, (2021)"},{"key":"359_CR237","unstructured":"Hendrycks, D., Burns, C., Kadavath, S., Arora, A., Basart, S., Tang, E., Song, D., Steinhardt, J.: Measuring mathematical problem solving with the MATH dataset. CoRR, vol. abs\/2103.03874, (2021)"},{"key":"359_CR238","doi-asserted-by":"crossref","unstructured":"Zellers, R., Holtzman, A., Bisk, Y., Farhadi, A., Choi, Y.: Hellaswag: can a machine really finish your sentence?\u201d arXiv:1905.07830v1, (2019)","DOI":"10.18653\/v1\/P19-1472"},{"key":"359_CR239","unstructured":"Clark, P., Cowhey, I., Etzioni, O., Khot, T., Sabharwal, A., Schoenick, C., Tafjord, O.: Think you have solved question answering? try arc, the AI2 reasoning challenge. CoRR, vol. abs\/1803.05457, 2018, Available: http:\/\/arxiv.org\/abs\/1803.05457."},{"key":"359_CR240","unstructured":"Bisk, Y., Zellers, R., Gao, J., Choi, Y.: PIQA: reasoning about physical commonsense in natural language. CoRR, vol. abs\/1911.11641, Available: http:\/\/arxiv.org\/abs\/1911.11641, (2019)"},{"key":"359_CR241","unstructured":"Sap, M., Rashkin, H., Chen, D., LeBras, R., Choi, Y.: Socialiqa: commonsense reasoning about social interactions. CoRR, vol. abs\/1904.09728, Available: http:\/\/arxiv.org\/abs\/1904.09728, (2019)"},{"key":"359_CR242","doi-asserted-by":"crossref","unstructured":"Mihaylov, T., Clark, P., Khot, T., Sabharwal, A.: Can a suit of armor conduct electricity? A new dataset for open book question answering. CoRR, vol. abs\/1809.02789, Available: http:\/\/arxiv.org\/abs\/1809.02789, (2018)","DOI":"10.18653\/v1\/D18-1260"},{"key":"359_CR243","doi-asserted-by":"crossref","unstructured":"Lin, S., Hilton, J., Evans, O.: Truthfulqa: measuring how models mimic human falsehoods. arXiv preprint arXiv:2109.07958, (2021)","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"359_CR244","doi-asserted-by":"crossref","unstructured":"Yang, Z., Qi, P., Zhang, S., Bengio, Y., Cohen, W.W., Salakhutdinov, R. & Manning, C.D.: Hotpotqa: a dataset for diverse, explainable multi-hop question answering. CoRR, vol. abs\/1809.09600, 2018. Available: http:\/\/arxiv.org\/abs\/1809.09600, (2018)","DOI":"10.18653\/v1\/D18-1259"},{"key":"359_CR245","unstructured":"Zhuang, Y., Yu, Y., Wang, K., Sun, H., Zhang, C.: Toolqa: a dataset for llm question answering with external tools. arXiv preprint arXiv:2306.13304, (2023)"},{"key":"359_CR246","doi-asserted-by":"publisher","first-page":"105603","DOI":"10.1016\/j.compag.2020.105603","volume":"175","author":"F Zhu","year":"2020","unstructured":"Zhu, F., He, M., Zheng, Z.: Data augmentation using improved cdcgan for plant vigor rating. Comput. Electron. Agric. 175, 105603 (2020)","journal-title":"Comput. Electron. Agric."},{"issue":"5","key":"359_CR247","first-page":"1","volume":"293","author":"JJ Bird","year":"2022","unstructured":"Bird, J.J., Barnes, C.M., Manso, L.J., Ek\u00e1rt, A., Faria, D.R.: Fruit quality and defect image classification with conditional GAN data augmentation. Sci. Hortic. 293(5), 1\u201311 (2022)","journal-title":"Sci. Hortic."},{"key":"359_CR248","doi-asserted-by":"publisher","first-page":"583438","DOI":"10.3389\/fpls.2020.583438","volume":"11","author":"L Bi","year":"2020","unstructured":"Bi, L., Hu, L.: Improving image-based plant disease classification with generative adversarial network under limited training set. Front. Plant Sci. 11, 583438 (2020)","journal-title":"Front. Plant Sci."},{"key":"359_CR249","unstructured":"Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J., Aila, T.: Training generative adversarial networks with limited data. In: Proceedings of 34th Conference on Neural Information Processing Systems vol. 33, pp. 12104\u201312114, (2020)"},{"key":"359_CR250","doi-asserted-by":"publisher","first-page":"103329","DOI":"10.1016\/j.cviu.2021.103329","volume":"215","author":"A Borji","year":"2022","unstructured":"Borji, A.: Pros and cons of GAN evaluation measures: new developments. Comput. Vis. Image Underst. 215, 103329 (2022)","journal-title":"Comput. Vis. Image Underst."},{"key":"359_CR251","doi-asserted-by":"publisher","first-page":"773142","DOI":"10.3389\/fpls.2021.773142","volume":"12","author":"M Xu","year":"2022","unstructured":"Xu, M., Yoon, S., Fuentes, A., Yang, J., Park, D.S.: Style-consistent image translation: a novel data augmentation paradigm to improve plant disease recognition. Front. Plant Sci. 12, 773142\u2013773142 (2022)","journal-title":"Front. Plant Sci."},{"issue":"12","key":"359_CR252","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3571730","volume":"55","author":"Z Ji","year":"2023","unstructured":"Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y.J., Madotto, A., Fung, P.: Survey of hallucination in natural language generation. ACM Comput. Surv. 55(12), 1\u201338 (2023)","journal-title":"ACM Comput. Surv."},{"key":"359_CR253","doi-asserted-by":"crossref","unstructured":"Wolfe, R., Banaji, MR., Caliskan, A.: Evidence for hypodescent in visual semantic AI. Evidence for hypodescent in visual semantic AI. In: Proceedings of ACM Conference on Fairness, Accountability, and Transparency, pp. 1293\u20131304, (2022)","DOI":"10.1145\/3531146.3533185"},{"key":"359_CR254","unstructured":"Birhane, A., Prabhu, V.U., Kahembwe, E.: Multimodal datasets: misogyny, pornography, and malignant stereotypes. arXiv:2110. 01963, (2021)"},{"key":"359_CR255","unstructured":"\u201cOpenAI (2023b) How should AI systems behave, and who should decide?\u201d https:\/\/openai.com\/blog\/how-should-ai-systems-behave [Last Accessed 11 June 2024]."},{"key":"359_CR256","unstructured":"\u201chttps:\/\/ensarseker1.medium.com\/4-horsemen-of-the-apocalypse-wormgpt-fraudgpt-xxxgpt-wolfgpt-bonus-evilgpt-5944372575b8\u201d, [Last Accessed 15 September 2024]."},{"key":"359_CR257","unstructured":"Kerdegari, H., Razaak, M., Argyriou, V., Remagnino, P.: Semi-supervised GAN for classification of multispectral imagery acquired by UAVs. arXiv preprint arXiv: 1905.10920, (2019)"},{"key":"359_CR258","doi-asserted-by":"crossref","unstructured":"Kierdorf, J., Weber, I., Kicherer, A., Zabawa, L., Drees, L. & Roscher, R.: Behind the leaves\u2014estimation of occluded grapevine berries with conditional generative adversarial networks. arXiv preprint arXiv:2105.10325, (2021)","DOI":"10.3389\/frai.2022.830026"},{"key":"359_CR259","doi-asserted-by":"crossref","unstructured":"Durall, R., Chatzimichailidis, A., Labus, P. and Keuper, J.: Combating mode collapse in GAN training: an empirical analysis using hessian eigenvalues. arXiv preprint arXiv: 2012.09673, (2020)","DOI":"10.5220\/0010167902110218"}],"container-title":["Progress in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13748-024-00359-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13748-024-00359-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13748-024-00359-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T13:03:27Z","timestamp":1748523807000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13748-024-00359-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,18]]},"references-count":259,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["359"],"URL":"https:\/\/doi.org\/10.1007\/s13748-024-00359-4","relation":{},"ISSN":["2192-6352","2192-6360"],"issn-type":[{"value":"2192-6352","type":"print"},{"value":"2192-6360","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,18]]},"assertion":[{"value":"21 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 December 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article contains no studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}