{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T11:12:09Z","timestamp":1783768329821,"version":"3.55.0"},"reference-count":145,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"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":["Multimedia Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s00530-026-02288-9","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:13:47Z","timestamp":1778048027000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A survey of large language models: techniques, applications, and challenges"],"prefix":"10.1007","volume":"32","author":[{"given":"Jiajie","family":"Ji","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueqing","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,6]]},"reference":[{"key":"2288_CR1","doi-asserted-by":"publisher","first-page":"9459","DOI":"10.48550\/arXiv.2005.11401","volume":"34","author":"P Lewis","year":"2021","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive nlp tasks. Adv. Neural. Inf. Process. Syst. 34, 9459\u20139474 (2021). https:\/\/doi.org\/10.48550\/arXiv.2005.11401","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2288_CR2","doi-asserted-by":"publisher","first-page":"5998","DOI":"10.48550\/arXiv.1706.03762","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural. Inf. Process. Syst. 30, 5998\u20136008 (2017). https:\/\/doi.org\/10.48550\/arXiv.1706.03762","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2288_CR3","unstructured":"Devlin, J., Chang, M.-W., et al.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv Preprint, 4171\u20134186 (2018) https:\/\/doi.org\/10.48550\/arXiv.1810.04805"},{"key":"2288_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106504","volume":"213","author":"A Bailly","year":"2022","unstructured":"Bailly, A., et al.: Effects of dataset size and interactions on the prediction performance of logistic regression and deep learning models. Comput. Methods Programs Biomed. 213, 106504 (2022). https:\/\/doi.org\/10.1016\/j.cmpb.2021.106504","journal-title":"Comput. Methods Programs Biomed."},{"key":"2288_CR5","doi-asserted-by":"crossref","unstructured":"Yin, S., Fu, C., et al.: A survey on multimodal large language models. National Science Review 11(12), 403 (2024) https:\/\/doi.org\/10.48550\/arXiv.1810.0480510.1093\/nsr\/nwae403 [cs.CV]","DOI":"10.1093\/nsr\/nwae403"},{"issue":"5","key":"2288_CR6","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1016\/j.fmre.2021.08.009","volume":"1","author":"C Wang","year":"2021","unstructured":"Wang, C., Zhang, N., Wang, C.: Managing privacy in the digital economy. Fundamental Res 1(5), 543\u2013551 (2021). https:\/\/doi.org\/10.1016\/j.fmre.2021.08.009","journal-title":"Fundamental Res"},{"issue":"12","key":"2288_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3571730","volume":"55","author":"G Ji","year":"2023","unstructured":"Ji, G., et al.: Survey of hallucination in natural language generation. ACM Comput. Surv. 55(12), 1\u201338 (2023). https:\/\/doi.org\/10.1145\/3571730","journal-title":"ACM Comput. Surv."},{"key":"2288_CR8","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.48550\/arXiv.2005.14165","volume":"33","author":"TB Brown","year":"2020","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020). https:\/\/doi.org\/10.48550\/arXiv.2005.14165","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2288_CR9","unstructured":"Radford, A., Narasimhan, K.: Improving language understanding by generative pre-training. (2018). https:\/\/api.semanticscholar.org\/CorpusID:49313245"},{"key":"2288_CR10","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.-W., Lee, K., et al.: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv e-prints, 1810\u201304805 (2018) https:\/\/doi.org\/10.48550\/arXiv.1810.04805arXiv:1810.04805 [cs.CL]","DOI":"10.48550\/arXiv.1810.04805"},{"issue":"8","key":"2288_CR11","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), 9 (2019)https:\/\/api.semanticscholar.org\/CorpusID:160025533","journal-title":"OpenAI Blog"},{"key":"2288_CR12","unstructured":"Brown, T.B., Mann, B., Ryder, N., et al.: Language Models are Few-Shot Learners. arXiv e-prints, 2005\u201314165 (2020) https:\/\/doi.org\/10.48550\/arXiv.2005.14165 [cs.CL]"},{"key":"2288_CR13","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et al.: Learning Transferable Visual Models From Natural Language Supervision. arXiv e-prints, 2103\u201300020 (2021) https:\/\/doi.org\/10.48550\/arXiv.2103.00020 [cs.CV]"},{"key":"2288_CR14","unstructured":"Chowdhery, A., et al.: Palm: Scaling language modeling with pathways. arXiv e-prints, 2204\u201302311 (2022) https:\/\/doi.org\/10.48550\/arXiv.2204.02311 [cs.CL]"},{"key":"2288_CR15","unstructured":"Raffel, C., et al.: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. arXiv e-prints, 1910\u201310683 (2019) https:\/\/doi.org\/10.48550\/arXiv.1910.10683 [cs.LG]"},{"key":"2288_CR16","unstructured":"OpenAI, et al.: GPT-4 Technical Report. arXiv e-prints, 2303\u201308774 (2023) https:\/\/doi.org\/10.48550\/arXiv.2303.08774 [cs.CL]"},{"key":"2288_CR17","doi-asserted-by":"publisher","unstructured":"Peters, M.E., et al.: Deep contextualized word representations. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 2227\u20132237 (2018). https:\/\/doi.org\/10.18653\/v1\/N18-1202","DOI":"10.18653\/v1\/N18-1202"},{"key":"2288_CR18","unstructured":"Liu, Y., et al.: Roberta: A robustly optimized bert pretraining approach. arXiv Preprint, 1218\u20131227 (2019) https:\/\/doi.org\/10.48550\/arXiv.1907.11692"},{"key":"2288_CR19","unstructured":"Sanh, V., Debut, L., et al.: Distilbert, a distilled version of bert: Smaller, faster, cheaper and lighter. arXiv Preprint (2019) https:\/\/doi.org\/10.48550\/arXiv.1910.01108"},{"key":"2288_CR20","unstructured":"Sanh, V., Debut, L., Chaumond, et al.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv e-prints, 1910\u201301108 (2019) https:\/\/doi.org\/10.48550\/arXiv.1910.01108 [cs.CL]"},{"key":"2288_CR21","doi-asserted-by":"publisher","first-page":"7059","DOI":"10.48550\/arXiv.1901.07291","volume":"32","author":"G Lample","year":"2019","unstructured":"Lample, G., Conneau, A.: Cross-lingual language model pretraining. Adv. Neural. Inf. Process. Syst. 32, 7059\u20137070 (2019). https:\/\/doi.org\/10.48550\/arXiv.1901.07291","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2288_CR22","doi-asserted-by":"publisher","first-page":"5753","DOI":"10.48550\/arXiv.1906.08237","volume":"32","author":"Z Yang","year":"2019","unstructured":"Yang, Z., et al.: Xlnet: Generalized autoregressive pretraining for language understanding. Adv. Neural. Inf. Process. Syst. 32, 5753\u20135763 (2019). https:\/\/doi.org\/10.48550\/arXiv.1906.08237","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2288_CR23","unstructured":"Lan, Z., Chen, M., Goodman, et al.: ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. arXiv e-prints, 1909\u201311942 (2019) https:\/\/doi.org\/10.48550\/arXiv.1909.11942 [cs.CL]"},{"key":"2288_CR24","unstructured":"Clark, K., Luong, M.-T., et al.: ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators. arXiv e-prints, 2003\u201310555 (2020) https:\/\/doi.org\/10.48550\/arXiv.2003.10555 [cs.CL]"},{"key":"2288_CR25","unstructured":"Chi, Z., Huang, S., Dong, L., Ma, S., Zheng, B., Singhal, S., Bajaj, P., Song, X., Mao, X.-L., Huang, H., Wei, F.: XLM-E: Cross-lingual Language Model Pre-training via ELECTRA. arXiv e-prints, 2106\u201316138 (2021) https:\/\/doi.org\/10.48550\/arXiv.2106.16138 [cs.CL]"},{"key":"2288_CR26","unstructured":"Du, Z., et al.: GLM: General Language Model Pretraining with Autoregressive Blank Infilling. arXiv e-prints, 2103\u201310360 (2021) https:\/\/doi.org\/10.48550\/arXiv.2103.10360 [cs.CL]"},{"key":"2288_CR27","unstructured":"Smith, S., et al.: Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model. arXiv e-prints, 2201\u201311990 (2022) https:\/\/doi.org\/10.48550\/arXiv.2201.11990 [cs.CL]"},{"key":"2288_CR28","unstructured":"Thoppilan, R., De Freitas, D., Hall, et al.: LaMDA: Language Models for Dialog Applications. arXiv e-prints, 2201\u201308239 (2022) https:\/\/doi.org\/10.48550\/arXiv.2201.08239 [cs.CL]"},{"key":"2288_CR29","doi-asserted-by":"publisher","unstructured":"Harahus, M., Sokolov\u00e1, Z., Pleva, M., Hl\u00e1dek, D.: Fine-tuning gpt-j for text generation tasks in the slovak language. In: 2024 IEEE 22nd World Symposium on Applied Machine Intelligence and Informatics (SAMI), pp. 455\u2013460 (2024). https:\/\/doi.org\/10.1109\/SAMI60510.2024.10432910","DOI":"10.1109\/SAMI60510.2024.10432910"},{"key":"2288_CR30","unstructured":"Scao, T.L., et al.: Bloom: A 176b-parameter open-access multilingual language model. arXiv Preprint (2022) https:\/\/doi.org\/10.48550\/arXiv.2211.05100"},{"key":"2288_CR31","doi-asserted-by":"publisher","unstructured":"Zhang, S., Roller, S., Goyal, et al.: OPT: Open Pre-trained Transformer Language Models. arXiv e-prints, 2205\u201301068 (2022) https:\/\/doi.org\/10.48550\/arXiv.2205.01068arXiv:2205.01068 [cs.CL]","DOI":"10.48550\/arXiv.2205.01068"},{"key":"2288_CR32","unstructured":"Rae, J.W., et al.: Scaling Language Models: Methods, Analysis & Insights from Training Gopher. arXiv e-prints, 2112\u201311446 (2021) https:\/\/doi.org\/10.48550\/arXiv.2112.11446 [cs.CL]"},{"key":"2288_CR33","doi-asserted-by":"publisher","first-page":"26783","DOI":"10.48550\/arXiv.2203.15556","volume":"35","author":"J Hoffmann","year":"2022","unstructured":"Hoffmann, J., et al.: Training compute-optimal large language models. Adv. Neural. Inf. Process. Syst. 35, 26783\u201326796 (2022). https:\/\/doi.org\/10.48550\/arXiv.2203.15556","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2288_CR34","unstructured":"Touvron, H., Martin, et al.: Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv e-prints, 2307\u201309288 (2023) https:\/\/doi.org\/10.48550\/arXiv.2307.09288 [cs.CL]"},{"key":"2288_CR35","unstructured":"OpenAI, : Jaech, A., et al.: OpenAI o1 System Card. arXiv e-prints, 2412\u201316720 (2024) https:\/\/doi.org\/10.48550\/arXiv.2412.16720 [cs.AI]"},{"key":"2288_CR36","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. arXiv e-prints, 7871\u20137880 (2019) https:\/\/doi.org\/10.48550\/arXiv.1910.13461 [cs.CL]","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"2288_CR37","doi-asserted-by":"publisher","unstructured":"Zhang, J., et al.: PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization. arXiv e-prints, 1912\u201308777 (2019) https:\/\/doi.org\/10.48550\/arXiv.1912.08777arXiv:1912.08777 [cs.CL]","DOI":"10.48550\/arXiv.1912.08777"},{"key":"2288_CR38","doi-asserted-by":"publisher","unstructured":"Lee, C.-H., et al.: DOCmT5: Document-Level Pretraining of Multilingual Language Models. arXiv e-prints, 2112\u201308709 (2021) https:\/\/doi.org\/10.48550\/arXiv.2112.08709 [cs.CL]","DOI":"10.48550\/arXiv.2112.08709"},{"key":"2288_CR39","unstructured":"Longpre, S., et al.: The Flan Collection: Designing Data and Methods for Effective Instruction Tuning. arXiv e-prints, 2301\u201313688 (2023) https:\/\/doi.org\/10.48550\/arXiv.2301.13688 [cs.AI]"},{"key":"2288_CR40","unstructured":"Tay, Y., et al.: UL2: Unifying Language Learning Paradigms. arXiv e-prints, 2205\u201305131 (2022) https:\/\/doi.org\/10.48550\/arXiv.2205.05131 [cs.CL]"},{"key":"2288_CR41","unstructured":"Fedus, W., Zoph, B., Shazeer, N.: Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity. arXiv e-prints, 2101\u201303961 (2021) https:\/\/doi.org\/10.48550\/arXiv.2101.03961 [cs.LG]"},{"key":"2288_CR42","unstructured":"Soltan, S., et al.: AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model. arXiv e-prints, 2208\u201301448 (2022) https:\/\/doi.org\/10.48550\/arXiv.2208.01448 [cs.CL]"},{"key":"2288_CR43","unstructured":"Arteaga, G.Y., Sch\u00f6n, T.B., et al.: Hallucination Detection in LLMs: Fast and Memory-Efficient Fine-Tuned Models. arXiv e-prints, 2409\u201302976 (2024) https:\/\/doi.org\/10.48550\/arXiv.2409.02976 [cs.LG]"},{"key":"2288_CR44","unstructured":"Chen, M., Tworek, J., Jun, H., Yuan, Q., et al.: Evaluating Large Language Models Trained on Code. arXiv e-prints, 2107\u201303374 (2021) https:\/\/doi.org\/10.48550\/arXiv.2107.03374 [cs.LG]"},{"key":"2288_CR45","doi-asserted-by":"crossref","unstructured":"Zheng, L., Chiang, W.-L., Sheng, Y., Zhuang, S., Wu, Z., Zhuang, Y., Lin, Z., Li, Z., Li, D., Xing, E.P., Zhang, H., Gonzalez, J.E., Stoica, I.: Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. arXiv e-prints, 2306\u201305685 (2023) https:\/\/doi.org\/10.48550\/arXiv.2306.05685 [cs.CL]","DOI":"10.52202\/075280-2020"},{"key":"2288_CR46","unstructured":"Wang, A., Pruksachatkun, Y., Nangia, N., et al.: Superglue: A stickier benchmark for general-purpose language understanding systems. arXiv e-prints, 1905\u201300537 (2019) https:\/\/doi.org\/10.48550\/arXiv.1905.00537 [cs.CL]"},{"key":"2288_CR47","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2019.132306","volume":"404","author":"A Sherstinsky","year":"2020","unstructured":"Sherstinsky, A.: Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network. Physica D 404, 132306 (2020). https:\/\/doi.org\/10.1016\/j.physd.2019.132306.  [cs.LG]","journal-title":"Physica D"},{"key":"2288_CR48","unstructured":"Bakke Venner\u00f8d, C., Kj\u00e6rran, A., Stray Bugge, E.: Long Short-term Memory RNN. arXiv e-prints, 2105\u201306756 (2021) https:\/\/doi.org\/10.48550\/arXiv.2105.06756 [cs.LG]"},{"issue":"12","key":"2288_CR49","doi-asserted-by":"publisher","first-page":"6999","DOI":"10.1109\/TNNLS.2021.3084827","volume":"33","author":"Z Li","year":"2022","unstructured":"Li, Z., Liu, F., Yang, W., Peng, S., Zhou, J.: A survey of convolutional neural networks: analysis, applications, and prospects. IEEE Trans. Neural Netw. Learn. Syst. 33(12), 6999\u20137019 (2022). https:\/\/doi.org\/10.1109\/TNNLS.2021.3084827","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"2288_CR50","doi-asserted-by":"publisher","first-page":"4299","DOI":"10.48550\/arXiv.1706.03741","volume":"30","author":"PF Christiano","year":"2017","unstructured":"Christiano, P.F., et al.: Deep reinforcement learning from human preferences. Adv. Neural. Inf. Process. Syst. 30, 4299\u20134307 (2017). https:\/\/doi.org\/10.48550\/arXiv.1706.03741","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2288_CR51","doi-asserted-by":"publisher","first-page":"27730","DOI":"10.48550\/arXiv.2203.02155","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022). https:\/\/doi.org\/10.48550\/arXiv.2203.02155","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2288_CR52","doi-asserted-by":"publisher","first-page":"3008","DOI":"10.48550\/arXiv.2009.01325","volume":"33","author":"N Stiennon","year":"2020","unstructured":"Stiennon, N., et al.: Learning to summarize from human feedback. Adv. Neural. Inf. Process. Syst. 33, 3008\u20133021 (2020). https:\/\/doi.org\/10.48550\/arXiv.2009.01325","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2288_CR53","unstructured":"Xu, P., et al.: DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models. arXiv e-prints, 2401\u201306066 (2024) https:\/\/doi.org\/10.48550\/arXiv.2401.06066 [cs.CL]"},{"key":"2288_CR54","unstructured":"Xie, J., Chen, et al.: Calibrating Language Models with Adaptive Temperature Scaling. arXiv e-prints, 2409\u201319817 (2024) https:\/\/doi.org\/10.48550\/arXiv.2409.19817 [cs.LG]"},{"key":"2288_CR55","unstructured":"Schulman, J., Wolski, F., Dhariwal, et al.: Proximal Policy Optimization Algorithms. arXiv e-prints, 1707\u201306347 (2017) https:\/\/doi.org\/10.48550\/arXiv.1707.06347 [cs.LG]"},{"key":"2288_CR56","unstructured":"Cai, Y., et al.: Training-Free Group Relative Policy Optimization. arXiv e-prints, 2510\u201308191 (2025) https:\/\/doi.org\/10.48550\/arXiv.2510.08191 [cs.CL]"},{"key":"2288_CR57","unstructured":"DeepSeek-AI, Guo, D., Yang, D., Zhang, H., et al.: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arXiv e-prints, 2501\u201312948 (2025) https:\/\/doi.org\/10.48550\/arXiv.2501.12948 [cs.CL]"},{"key":"2288_CR58","unstructured":"Bai, Y., Jones, A., Ndousse, et al.: Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback. arXiv e-prints, 2204\u201305862 (2022) https:\/\/doi.org\/10.48550\/arXiv.2204.05862 [cs.CL]"},{"key":"2288_CR59","unstructured":"Evans, O., et al.: Truthful AI: Developing and governing AI that does not lie. arXiv e-prints, 2110\u201306674 (2021) https:\/\/doi.org\/10.48550\/arXiv.2110.06674 [cs.CY]"},{"key":"2288_CR60","unstructured":"Lambert, N.: Reinforcement Learning from Human Feedback. arXiv e-prints, 2504\u201312501 (2025) https:\/\/doi.org\/10.48550\/arXiv.2504.12501 [stat.ML]"},{"key":"2288_CR61","unstructured":"Wang, Y., Kordi, Y., et al.: Self-Instruct: Aligning Language Models with Self-Generated Instructions. arXiv e-prints, 2212\u201310560 (2022) https:\/\/doi.org\/10.48550\/arXiv.2212.10560 [cs.CL]"},{"key":"2288_CR62","unstructured":"Chung, H.W., Hou, L., Longpre, S., et al.: Scaling Instruction-Finetuned Language Models. arXiv e-prints, 2210\u201311416 (2022) https:\/\/doi.org\/10.48550\/arXiv.2210.11416 [cs.LG]"},{"key":"2288_CR63","doi-asserted-by":"crossref","unstructured":"Bi, B., et al.: PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation. arXiv e-prints, 2004\u201307159 (2020) https:\/\/doi.org\/10.48550\/arXiv.2004.07159 [cs.CL]","DOI":"10.18653\/v1\/2020.emnlp-main.700"},{"key":"2288_CR64","doi-asserted-by":"publisher","unstructured":"Narayanan, D., et al.: Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM. arXiv e-prints, 2104\u201304473 (2021) https:\/\/doi.org\/10.48550\/arXiv.2104.04473arXiv:2104.04473 [cs.CL]","DOI":"10.48550\/arXiv.2104.04473"},{"issue":"12","key":"2288_CR65","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3571730","volume":"55","author":"Z Ji","year":"2023","unstructured":"Ji, Z., et al.: Survey of hallucination in natural language generation. ACM Comput. Surv. 55(12), 1\u201338 (2023). https:\/\/doi.org\/10.1145\/3571730","journal-title":"ACM Comput. Surv."},{"key":"2288_CR66","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrm.2023.101119","volume":"4","author":"D Shen","year":"2023","unstructured":"Shen, D., Mo, Z., Zeng, M.: Fast and low-dose medical imaging generation empowered by hybrid deep-learning and iterative reconstruction. Cell Reports Med. 4, 101119 (2023). https:\/\/doi.org\/10.1016\/j.xcrm.2023.101119","journal-title":"Cell Reports Med."},{"key":"2288_CR67","unstructured":"Hu, Y., et al.: Planning-oriented Autonomous Driving. arXiv e-prints, 2212\u201310156 (2022) https:\/\/doi.org\/10.48550\/arXiv.2212.10156 [cs.CV]"},{"key":"2288_CR68","doi-asserted-by":"crossref","unstructured":"Sawarkar, K., Mangal, A., Solanki, S.R.: Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers. arXiv e-prints, 2404\u201307220 (2024) https:\/\/doi.org\/10.48550\/arXiv.2404.07220 [cs.IR]","DOI":"10.1109\/MIPR62202.2024.00031"},{"key":"2288_CR69","unstructured":"Zhao, M., et al.: Adversarial Training: A Survey. arXiv e-prints, 2410\u201315042 (2024) https:\/\/doi.org\/10.48550\/arXiv.2410.15042 [cs.LG]"},{"key":"2288_CR70","unstructured":"Bubeck, S., et al.: Sparks of Artificial General Intelligence: Early experiments with GPT-4. arXiv e-prints, 2303\u201312712 (2023) https:\/\/doi.org\/10.48550\/arXiv.2303.12712 [cs.CL]"},{"key":"2288_CR71","unstructured":"Wang, Y., et al.: Self-Instruct: Aligning Language Models with Self-Generated Instructions. arXiv e-prints, 2212\u201310560 (2022) https:\/\/doi.org\/10.48550\/arXiv.2212.10560 [cs.CL]"},{"issue":"7972","key":"2288_CR72","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","volume":"620","author":"K Singhal","year":"2023","unstructured":"Singhal, K., et al.: Large language models encode clinical knowledge. Nature 620(7972), 172\u2013180 (2023). https:\/\/doi.org\/10.1038\/s41586-023-06291-2","journal-title":"Nature"},{"issue":"4","key":"2288_CR73","doi-asserted-by":"publisher","first-page":"2460","DOI":"10.1016\/j.jds.2025.02.022","volume":"20","author":"Y Mine","year":"2025","unstructured":"Mine, Y., Taji, T., Okazaki, S., Takeda, S., Peng, T.-Y., Shimoe, S., Kaku, M., Nikawa, H., Kakimoto, N., Murayama, T.: Analyzing the performance of multimodal large language models on visually-based questions in the japanese national examination for dental technicians. J Dental Sci 20(4), 2460\u20132466 (2025). https:\/\/doi.org\/10.1016\/j.jds.2025.02.022","journal-title":"J Dental Sci"},{"key":"2288_CR74","doi-asserted-by":"publisher","unstructured":"Hazra, D., Mukherjee, S., Kumar, S., Chatterjee, S., Khan, P.W., Abbas, K.: Evaluating hallucination and diagnostic reliability of llms on medical image-based multiple choice tasks. IEEE Journal of Biomedical and Health Informatics PP, 1456\u20131463 (2025) https:\/\/doi.org\/10.1109\/JBHI.2025.3621146","DOI":"10.1109\/JBHI.2025.3621146"},{"issue":"6","key":"2288_CR75","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1080\/01605682.2024.2416908","volume":"76","author":"B Dong","year":"2025","unstructured":"Dong, B., Zhou, Y., Sun, X., Zhu, J.: Textual analysis and credit scoring: a new matrix factorization approach. J. Oper. Res. Soc. 76(6), 1189\u20131203 (2025). https:\/\/doi.org\/10.1080\/01605682.2024.2416908","journal-title":"J. Oper. Res. Soc."},{"issue":"3","key":"2288_CR76","doi-asserted-by":"publisher","first-page":"671","DOI":"10.15779\/Z38BG31","volume":"104","author":"S Barocas","year":"2016","unstructured":"Barocas, S., Hardt, M., Narayanan, A.: Big data\u2019s disparate impact. Calif. Law Rev. 104(3), 671\u2013732 (2016). https:\/\/doi.org\/10.15779\/Z38BG31","journal-title":"Calif. Law Rev."},{"key":"2288_CR77","doi-asserted-by":"publisher","unstructured":"Kasy, M., Abebe, R.: Fairness, equality, and power in algorithmic decision-making. In: Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency. FAccT \u201921, pp. 576\u2013586. Association for Computing Machinery, New York, NY, USA (2021). https:\/\/doi.org\/10.1145\/3442188.3445919","DOI":"10.1145\/3442188.3445919"},{"key":"2288_CR78","unstructured":"Li, X., et al.: Benchmarking Bias in Large Language Models during Role-Playing. arXiv e-prints, 2411\u201300585 (2024) https:\/\/doi.org\/10.48550\/arXiv.2411.00585 [cs.CY]"},{"key":"2288_CR79","doi-asserted-by":"publisher","first-page":"1567","DOI":"10.1109\/TLT.2024.3396873","volume":"17","author":"L Zhang","year":"2024","unstructured":"Zhang, L., et al.: Automated essay scoring and revising based on open-source large language models. IEEE Trans. Learn. Technol. 17, 1567\u20131580 (2024). https:\/\/doi.org\/10.1109\/TLT.2024.3396873","journal-title":"IEEE Trans. Learn. Technol."},{"key":"2288_CR80","doi-asserted-by":"publisher","unstructured":"Hang, C.N., Man Ho, S.: Personalized vocabulary learning through images: Harnessing multimodal large language models for early childhood education. In: 2025 IEEE Integrated STEM Education Conference (ISEC), pp. 1\u20137 (2025). https:\/\/doi.org\/10.1109\/ISEC64801.2025.11147254","DOI":"10.1109\/ISEC64801.2025.11147254"},{"key":"2288_CR81","doi-asserted-by":"publisher","unstructured":"Sapkota, S., Bhattarai, B.: Importance Estimation with Random Gradient for Neural Network Pruning. arXiv e-prints, 2310\u201320203 (2023) https:\/\/doi.org\/10.48550\/arXiv.2310.20203arXiv:2310.20203 [cs.LG]","DOI":"10.48550\/arXiv.2310.20203"},{"key":"2288_CR82","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the Knowledge in a Neural Network. arXiv e-prints, 1503\u201302531 (2015) https:\/\/doi.org\/10.48550\/arXiv.1503.02531 [stat.ML]"},{"key":"2288_CR83","unstructured":"Jacob, B., Kligys, S., et al.: Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference. arXiv e-prints, 1712\u201305877 (2017) https:\/\/doi.org\/10.48550\/arXiv.1712.05877 [cs.LG]"},{"key":"2288_CR84","unstructured":"Fan, A., Grave, E., Joulin, A.: Reducing Transformer Depth on Demand with Structured Dropout. arXiv e-prints, 1909\u201311556 (2019) https:\/\/doi.org\/10.48550\/arXiv.1909.11556 [cs.LG]"},{"key":"2288_CR85","unstructured":"Lin, J., Tang, J., Tang, H., et al.: AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration. arXiv e-prints, 2306\u201300978 (2023) https:\/\/doi.org\/10.48550\/arXiv.2306.00978 [cs.CL]"},{"issue":"5","key":"2288_CR86","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1038\/s42256-019-0048-x","volume":"1","author":"SM Lundberg","year":"2017","unstructured":"Lundberg, S.M., Lee, S.-I.: A unified approach to interpreting model predictions. Nat. Mach. Intell. 1(5), 227\u2013235 (2017). https:\/\/doi.org\/10.1038\/s42256-019-0048-x","journal-title":"Nat. Mach. Intell."},{"key":"2288_CR87","unstructured":"Li, Z., Zhang, N., Yao, et al.: Unveiling the Pitfalls of Knowledge Editing for Large Language Models. arXiv e-prints, 2310\u201302129 (2023) https:\/\/doi.org\/10.48550\/arXiv.2310.02129 [cs.CL]"},{"issue":"1","key":"2288_CR88","doi-asserted-by":"publisher","first-page":"1953","DOI":"10.1038\/s41598-022-05539-7","volume":"12","author":"M Adnan","year":"2022","unstructured":"Adnan, M., et al.: Federated learning and differential privacy for medical image analysis. Sci. Rep. 12(1), 1953 (2022). https:\/\/doi.org\/10.1038\/s41598-022-05539-7","journal-title":"Sci. Rep."},{"key":"2288_CR89","unstructured":"Kang, Y., Li, J., Liu, Y., Wang, W.: Data Heterogeneity Differential Privacy: From Theory to Algorithm. arXiv e-prints, 2002\u201308578 (2020) https:\/\/doi.org\/10.48550\/arXiv.2002.08578 [cs.LG]"},{"issue":"1","key":"2288_CR90","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1109\/TC.2024.3477971","volume":"74","author":"B Zhang","year":"2025","unstructured":"Zhang, B., Mao, Y., He, X., Huang, H., Wu, J.: Balancing privacy and accuracy using significant gradient protection in federated learning. IEEE Trans. Comput. 74(1), 278\u2013292 (2025). https:\/\/doi.org\/10.1109\/TC.2024.3477971","journal-title":"IEEE Trans. Comput."},{"key":"2288_CR91","unstructured":"Aldaghri, N., Mahdavifar, H., Beirami, A.: Federated Learning with Heterogeneous Differential Privacy. arXiv e-prints, 2110\u201315252 (2021) https:\/\/doi.org\/10.48550\/arXiv.2110.15252 [cs.LG]"},{"key":"2288_CR92","unstructured":"Mandal, D., Nika, A., Kamalaruban, P., et al.: Corruption Robust Offline Reinforcement Learning with Human Feedback. arXiv e-prints, 2402\u201306734 (2024) https:\/\/doi.org\/10.48550\/arXiv.2402.06734 [cs.LG]"},{"key":"2288_CR93","unstructured":"Izacard, G., et al.: Atlas: Few-shot Learning with Retrieval Augmented Language Models. arXiv e-prints, 2208\u201303299 (2022) https:\/\/doi.org\/10.48550\/arXiv.2208.03299 [cs.CL]"},{"key":"2288_CR94","doi-asserted-by":"publisher","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pp. 6769\u20136781 (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.550","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"2288_CR95","doi-asserted-by":"publisher","unstructured":"Chen, Z., et al.: Improving Retrieval Augmented Open-Domain Question-Answering with Vectorized Contexts. arXiv e-prints, 7683\u20137694 (2024) https:\/\/doi.org\/10.48550\/arXiv.2404.02022arXiv:2404.02022 [cs.CL]","DOI":"10.48550\/arXiv.2404.02022"},{"key":"2288_CR96","unstructured":"Xie, R., et al.: Interleaved Reasoning for Large Language Models via Reinforcement Learning. arXiv e-prints, 2505\u201319640 (2025)  https:\/\/doi.org\/10.48550\/arXiv.2505.19640 [cs.CL]"},{"key":"2288_CR97","doi-asserted-by":"publisher","unstructured":"Jiang, A.Q., et al.: Mistral 7b. arXiv preprint , 1\u201310 (2023) https:\/\/doi.org\/10.48550\/arXiv.2310.06825","DOI":"10.48550\/arXiv.2310.06825"},{"key":"2288_CR98","doi-asserted-by":"publisher","first-page":"5505","DOI":"10.48550\/arXiv.2305.11206","volume":"36","author":"C Zhou","year":"2023","unstructured":"Zhou, C., Levy, O., Zettlemoyer, L., Ghazvininejad, M.: Lima: Less is more for alignment. Adv. Neural. Inf. Process. Syst. 36, 5505\u20135521 (2023). https:\/\/doi.org\/10.48550\/arXiv.2305.11206","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2288_CR99","doi-asserted-by":"publisher","unstructured":"Yao, S., Zhao, J., et al.: React: Synergizing reasoning and acting in language models. In: Proceedings of the International Conference on Learning Representations (2023). https:\/\/doi.org\/10.48550\/arXiv.2210.03629","DOI":"10.48550\/arXiv.2210.03629"},{"key":"2288_CR100","unstructured":"Xi, Z., et al.: The Rise and Potential of Large Language Model Based Agents: A Survey. arXiv e-prints, 2309\u201307864 (2023) https:\/\/doi.org\/10.48550\/arXiv.2309.07864 [cs.AI]"},{"key":"2288_CR101","doi-asserted-by":"crossref","unstructured":"Schick, T., et al.: Toolformer: Language Models Can Teach Themselves to Use Tools. arXiv e-prints, 2302\u201304761 (2023) https:\/\/doi.org\/10.48550\/arXiv.2302.04761 [cs.CL]","DOI":"10.52202\/075280-2997"},{"key":"2288_CR102","doi-asserted-by":"publisher","unstructured":"Shinn, N., Cassano, F., et al.: Reflexion: Language agents with verbal reinforcement learning. In: Proceedings of the 37th Conference on Neural Information Processing Systems (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.11366","DOI":"10.48550\/arXiv.2303.11366"},{"key":"2288_CR103","doi-asserted-by":"publisher","first-page":"51987","DOI":"10.48550\/arXiv.2303.17760","volume":"36","author":"G Li","year":"2023","unstructured":"Li, G., et al.: Camel: Communicative agents for\u201c mind\u2019\u2019 exploration of large language model society. Adv. Neural. Inf. Process. Syst. 36, 51987\u201352007 (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.17760","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2288_CR104","unstructured":"Qin, Y., Hu, S., Lin, Y., et al.: Tool Learning with Foundation Models. arXiv e-prints, 2304\u201308354 (2023) https:\/\/doi.org\/10.48550\/arXiv.2304.08354 [cs.CL]"},{"key":"2288_CR105","unstructured":"Liu, Y., et al.: Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study. arXiv e-prints, 2305\u201313860 (2023) https:\/\/doi.org\/10.48550\/arXiv.2305.13860 [cs.SE]"},{"key":"2288_CR106","doi-asserted-by":"crossref","unstructured":"Qiao, S., et al.: Reasoning with language model prompting: A survey. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 5368\u20135393. Association for Computational Linguistics, Toronto, Canada (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.294.","DOI":"10.18653\/v1\/2023.acl-long.294"},{"key":"2288_CR107","unstructured":"Chen, S., Wong, S., Chen, L., Tian, Y.: Extending Context Window of Large Language Models via Positional Interpolation. arXiv e-prints, 2306\u201315595 (2023) https:\/\/doi.org\/10.48550\/arXiv.2306.15595 [cs.CL]"},{"key":"2288_CR108","doi-asserted-by":"crossref","unstructured":"Valmeekam, K., Marquez, M., Sreedharan, et al.: On the Planning Abilities of Large Language Models : A Critical Investigation. arXiv e-prints, 2305\u201315771 (2023) https:\/\/doi.org\/10.48550\/arXiv.2305.15771 [cs.AI]","DOI":"10.52202\/075280-3320"},{"key":"2288_CR109","unstructured":"Pope, R., Douglas, S., Chowdhery, et al.: Efficiently Scaling Transformer Inference. arXiv e-prints, 2211\u201305102 (2022) https:\/\/doi.org\/10.48550\/arXiv.2211.05102 [cs.LG]"},{"key":"2288_CR110","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Fang, M., Chen, L.: RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering. arXiv e-prints, 2402\u201316457 (2024) https:\/\/doi.org\/10.48550\/arXiv.2402.16457 [cs.CL]","DOI":"10.18653\/v1\/2024.findings-acl.415"},{"key":"2288_CR111","unstructured":"Hartsock, I., Araujo, C., Folio, L., Rasool, G.: Improving Radiology Report Conciseness and Structure via Local Large Language Models. arXiv e-prints, 2411\u201305042 (2024) https:\/\/doi.org\/10.48550\/arXiv.2411.05042 [cs.CL]"},{"key":"2288_CR112","unstructured":"Bai, T., et al.: A Survey of Multimodal Large Language Model from A Data-centric Perspective. arXiv e-prints, 2405\u201316640 (2024) https:\/\/doi.org\/10.48550\/arXiv.2405.16640 [cs.AI]"},{"key":"2288_CR113","unstructured":"Ganguli, D., et al.: Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned. arXiv e-prints, 2209\u201307858 (2022) https:\/\/doi.org\/10.48550\/arXiv.2209.07858 [cs.CL]"},{"key":"2288_CR114","unstructured":"Lightman, H., Kosaraju, V., Burda, et al.: Let\u2019s Verify Step by Step. arXiv e-prints, 2305\u201320050 (2023) https:\/\/doi.org\/10.48550\/arXiv.2305.20050 [cs.LG]"},{"key":"2288_CR115","doi-asserted-by":"publisher","unstructured":"Benato, B.C., Telea, A.C., Falc\u00e3o, A.X.: Iterative pseudo-labeling with deep feature annotation and confidence-based sampling. In: 2021 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 192\u2013198 (2021). https:\/\/doi.org\/10.1109\/SIBGRAPI54419.2021.00034","DOI":"10.1109\/SIBGRAPI54419.2021.00034"},{"key":"2288_CR116","doi-asserted-by":"publisher","unstructured":"Cubuk, E.D., et al.: Autoaugment: Learning augmentation strategies from data. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 113\u2013123 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00020","DOI":"10.1109\/CVPR.2019.00020"},{"key":"2288_CR117","unstructured":"Chen, R., Wang, L.: The Power of Active Multi-Task Learning in Reinforcement Learning from Human Feedback. arXiv e-prints, 2405\u201311226 (2024) https:\/\/doi.org\/10.48550\/arXiv.2405.11226 [cs.LG]"},{"key":"2288_CR118","unstructured":"Bai, H., Cao, et al.: Self-supervised Semi-supervised Learning for Data Labeling and Quality Evaluation. arXiv e-prints, 2111\u201310932 (2021) https:\/\/doi.org\/10.48550\/arXiv.2111.10932 [cs.CV]"},{"key":"2288_CR119","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2023.103714","volume":"220","author":"BS Guendouzi","year":"2023","unstructured":"Guendouzi, B.S., et al.: A systematic review of federated learning: Challenges, aggregation methods, and development tools. J. Netw. Comput. Appl. 220, 103714 (2023). https:\/\/doi.org\/10.1016\/j.jnca.2023.103714","journal-title":"J. Netw. Comput. Appl."},{"key":"2288_CR120","doi-asserted-by":"crossref","unstructured":"Hwang, M., Lee, G., Kee, H., et al.: Sequential preference ranking for efficient reinforcement learning from human feedback 36, 49088\u201349099 (2023) https:\/\/www.scopus.com\/pages\/publications\/85205444329","DOI":"10.52202\/075280-2133"},{"key":"2288_CR121","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Factuality of Large Language Models: A Survey. arXiv e-prints, 19519\u201319529 (2024) https:\/\/doi.org\/10.48550\/arXiv.2402.02420 [cs.CL]","DOI":"10.18653\/v1\/2024.emnlp-main.1088"},{"key":"2288_CR122","unstructured":"Sun, H., Chai, Y., Wang, S., et al.: Curiosity-Driven Reinforcement Learning from Human Feedback. arXiv e-prints, 2501\u201311463 (2025) https:\/\/doi.org\/10.48550\/arXiv.2501.11463 [cs.CL]"},{"key":"2288_CR123","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Long-form hallucination detection with self-elicitation. In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T. (eds.) Findings of the Association for Computational Linguistics: ACL 2025, pp. 4082\u20134100. Association for Computational Linguistics, Vienna, Austria (2024). https:\/\/doi.org\/10.18653\/v1\/2025.findings-acl.211.","DOI":"10.18653\/v1\/2025.findings-acl.211"},{"key":"2288_CR124","unstructured":"Buolamwini, J., Gebru, T.: Gender shades: Intersectional accuracy disparities in commercial gender classification. In: FAT, pp. 77\u201391 (2018). https:\/\/api.semanticscholar.org\/CorpusID:3298854"},{"key":"2288_CR125","unstructured":"Bian, S., et al.: Scaling Inference-Efficient Language Models. arXiv e-prints, 2501\u201318107 (2025) https:\/\/doi.org\/10.48550\/arXiv.2501.18107 [stat.ML]. To appear in NeurIPS 2025"},{"issue":"188","key":"2288_CR126","doi-asserted-by":"publisher","first-page":"1","DOI":"10.48550\/arXiv.2101.03961","volume":"23","author":"W Fedus","year":"2022","unstructured":"Fedus, W., Zoph, B., Shazeer, N.: Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. J. Mach. Learn. Res. 23(188), 1\u201334 (2022). https:\/\/doi.org\/10.48550\/arXiv.2101.03961","journal-title":"J. Mach. Learn. Res."},{"key":"2288_CR127","unstructured":"Aizpurua, B., et al.: Quantum Large Language Models via Tensor Network Disentanglers. arXiv e-prints, 2410\u201317397 (2024) https:\/\/doi.org\/10.48550\/arXiv.2410.17397 [quant-ph]"},{"key":"2288_CR128","unstructured":"Rallis, K., et al.: Hardware-level Interfaces for Hybrid Quantum-Classical Computing Systems. arXiv e-prints, 2503\u201318868 (2025) https:\/\/doi.org\/10.48550\/arXiv.2503.18868 [quant-ph]"},{"key":"2288_CR129","unstructured":"Kong, X., et al.: Quantum-Enhanced LLM Efficient Fine Tuning. arXiv e-prints, 2503\u201312790 (2025) https:\/\/doi.org\/10.48550\/arXiv.2503.12790 [quant-ph]"},{"key":"2288_CR130","unstructured":"Yan, X., et al.: Efficient Reinforcement Learning with Large Language Model Priors. arXiv e-prints, 2410\u201307927 (2024) https:\/\/doi.org\/10.48550\/arXiv.2410.07927 [cs.LG]"},{"key":"2288_CR131","unstructured":"Rho, D., et al.: Encryption-Friendly LLM Architecture. arXiv e-prints, 2410\u201302486 (2024) https:\/\/doi.org\/10.48550\/arXiv.2410.02486 [cs.CR]"},{"key":"2288_CR132","unstructured":"Zhao, G., Song, E.: Privacy-Preserving Large Language Models: Mechanisms, Applications, and Future Directions. arXiv e-prints, 2412\u201306113 (2024) https:\/\/doi.org\/10.48550\/arXiv.2412.06113 [cs.CR]"},{"key":"2288_CR133","doi-asserted-by":"publisher","unstructured":"Li, C., et al.: Ethical privacy framework for large language models in smart healthcare: A comprehensive evaluation and protection approach. IEEE Journal of Biomedical and Health Informatics, 1\u201314 (2025) https:\/\/doi.org\/10.1109\/JBHI.2025.3576579","DOI":"10.1109\/JBHI.2025.3576579"},{"key":"2288_CR134","doi-asserted-by":"publisher","unstructured":"Neil, R., Zanger-Tishler, M.: Algorithmic bias in criminal risk assessment: The consequences of racial differences in arrest as a measure of crime. Annual Review of Criminology 8(Volume 8, 2025), 97\u2013119 (2025) https:\/\/doi.org\/10.1146\/annurev-criminol-022422-125019","DOI":"10.1146\/annurev-criminol-022422-125019"},{"key":"2288_CR135","doi-asserted-by":"publisher","first-page":"6647","DOI":"10.55248\/gengpi.6.0325.12106","volume":"6","author":"C Umeaduma","year":"2025","unstructured":"Umeaduma, C., Adeniyi, A.: Ai-powered credit scoring models: ethical considerations, bias reduction, and financial inclusion strategies. Int J Res Publication and Rev 6, 6647\u20136661 (2025). https:\/\/doi.org\/10.55248\/gengpi.6.0325.12106","journal-title":"Int J Res Publication and Rev"},{"key":"2288_CR136","doi-asserted-by":"publisher","first-page":"3135","DOI":"10.36948\/ijfmr.2023.v05i03.3135","volume":"5","author":"S Pal","year":"2023","unstructured":"Pal, S.: The future of large language models: a futuristic dissection on ai and human interaction. Int J Multidisciplinary Res 5, 3135 (2023). https:\/\/doi.org\/10.36948\/ijfmr.2023.v05i03.3135","journal-title":"Int J Multidisciplinary Res"},{"key":"2288_CR137","doi-asserted-by":"publisher","unstructured":"Lokesh, G.R., et al.: Ai and the future of work: Preparing the workforce for technological shifts and skill evolution. In: 2024 International Conference on Knowledge Engineering and Communication Systems (ICKECS), vol. 1, pp. 1\u20136 (2024). https:\/\/doi.org\/10.1109\/ICKECS61492.2024.10616486","DOI":"10.1109\/ICKECS61492.2024.10616486"},{"key":"2288_CR138","doi-asserted-by":"publisher","unstructured":"Sharma, N., et al.: Generative echo chamber? effect of llm-powered search systems on diverse information seeking, pp. 1\u201317 (2024). https:\/\/doi.org\/10.1145\/3613904.3642459","DOI":"10.1145\/3613904.3642459"},{"key":"2288_CR139","doi-asserted-by":"publisher","DOI":"10.1016\/j.caeai.2024.100243","volume":"6","author":"A Stojanov","year":"2024","unstructured":"Stojanov, A., Liu, Q., Koh, J.H.L.: University students\u2019 self-reported reliance on chatgpt for learning: A latent profile analysis. Comput Education: Artif Intell 6, 100243 (2024). https:\/\/doi.org\/10.1016\/j.caeai.2024.100243","journal-title":"Comput Education: Artif Intell"},{"key":"2288_CR140","doi-asserted-by":"crossref","unstructured":"Sankaran, S.: Enhancing Trust Through Standards: A Comparative Risk-Impact Framework for Aligning ISO AI Standards with Global Ethical and Regulatory Contexts. arXiv e-prints, 2504\u201316139 (2025) https:\/\/doi.org\/10.48550\/arXiv.2504.16139 [cs.CY]","DOI":"10.1109\/ACDSA65407.2025.11166403"},{"key":"2288_CR141","doi-asserted-by":"crossref","unstructured":"Al-Maamari, A.: Between Innovation and Oversight: A Cross-Regional Study of AI Risk Management Frameworks in the EU, U.S., UK, and China. arXiv e-prints, 2503\u201305773 (2025) https:\/\/doi.org\/10.48550\/arXiv.2503.05773 [cs.CY]","DOI":"10.1109\/i-COSTE68047.2025.11467397"},{"issue":"8","key":"2288_CR142","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","volume":"29","author":"AJ Thirunavukarasu","year":"2023","unstructured":"Thirunavukarasu, A.J., et al.: Large language models in medicine. Nat. Med. 29(8), 1930\u20131940 (2023). https:\/\/doi.org\/10.1038\/s41591-023-02448-8","journal-title":"Nat. Med."},{"key":"2288_CR143","unstructured":"Nie, Y., et al.: A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challenges. arXiv e-prints, 2406\u201311903 (2024) https:\/\/doi.org\/10.48550\/arXiv.2406.11903 [q-fin.GN]"},{"key":"2288_CR144","unstructured":"Raffel, C., Ellis, D.P.W.: Feed-Forward Networks with Attention Can Solve Some Long-Term Memory Problems. arXiv e-prints, 1512\u201308756 (2015) https:\/\/doi.org\/10.48550\/arXiv.1512.08756 [cs.LG]"},{"key":"2288_CR145","unstructured":"Zhou, J., Ji, J., Dai, J., et al.: Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback. arXiv e-prints, 2409\u201300162 (2024) https:\/\/doi.org\/10.48550\/arXiv.2409.00162 [cs.CL]"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02288-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02288-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02288-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T10:19:24Z","timestamp":1783765164000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02288-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,6]]},"references-count":145,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["2288"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02288-9","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,6]]},"assertion":[{"value":"16 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2026","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 no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"303"}}