{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:41:20Z","timestamp":1776444080653,"version":"3.51.2"},"reference-count":171,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006754","name":"U.S. Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF-20-2-0277"],"award-info":[{"award-number":["W911NF-20-2-0277"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tai.2024.3444742","type":"journal-article","created":{"date-parts":[[2024,8,19]],"date-time":"2024-08-19T13:40:13Z","timestamp":1724074813000},"page":"5873-5893","source":"Crossref","is-referenced-by-count":101,"title":["Recent Advances in Generative AI and Large Language Models: Current Status, Challenges, and Perspectives"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2014-2749","authenticated-orcid":false,"given":"Desta Haileselassie","family":"Hagos","sequence":"first","affiliation":[{"name":"DoD Center of Excellence in Artificial Intelligence and Machine Learning (CoE-AIML), Department of Electrical Engineering and Computer Science, College of Engineering and Architecture (CEA), Howard University, Washington, DC, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2037-9878","authenticated-orcid":false,"given":"Rick","family":"Battle","sequence":"additional","affiliation":[{"name":"VMware AI Labs by Broadcom, Palo Alto, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3638-3464","authenticated-orcid":false,"given":"Danda B.","family":"Rawat","sequence":"additional","affiliation":[{"name":"DoD Center of Excellence in Artificial Intelligence and Machine Learning (CoE-AIML), Department of Electrical Engineering and Computer Science, College of Engineering and Architecture (CEA), Howard University, Washington, DC, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1176"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref5","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021"},{"key":"ref6","article-title":"Evaluating large language models trained on code","author":"Chen","year":"2021"},{"key":"ref7","first-page":"858","article-title":"Large language models in machine translation","volume-title":"Proc. Joint Conf. Empirical Methods Natural Lang. Process. Comput. Natural Lang. Learn.","author":"Brants","year":"2007"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/daed_a_01905"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3146347.3146358"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2014.6889433"},{"key":"ref11","first-page":"1","article-title":"Scaling infrastructure to support multi-trillion parameter LLM training","volume-title":"Proc. Archit. Syst. Support Transformer Models (ASSYST@ ISCA)","author":"Isaev","year":"2023"},{"key":"ref12","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref13","first-page":"30016","article-title":"An empirical analysis of compute-optimal large language model training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Hoffmann","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"issue":"64\u201367","key":"ref15","first-page":"p. 2","article-title":"Recurrent neural networks","volume":"5","author":"Medsker","year":"2001","journal-title":"Des. Appl."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170"},{"issue":"10","key":"ref17","first-page":"255","article-title":"Convolutional networks for images, speech, and time series","volume-title":"The Handbook of Brain Theory and Neural Networks","volume":"3361","author":"LeCun","year":"1995"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"1","key":"ref19","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref20","first-page":"1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin","year":"2019"},{"key":"ref21","first-page":"1","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref22","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby","year":"2019"},{"key":"ref23","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2013"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3269251"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref26","article-title":"LaMDA: Language models for dialog applications","author":"Thoppilan","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref28","first-page":"1","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Goodfellow","year":"2014"},{"key":"ref29","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"Radford","year":"2015"},{"key":"ref30","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arjovsky","year":"2017"},{"key":"ref31","article-title":"Progressive growing of GANs for improved quality, stability, and variation","author":"Karras","year":"2017"},{"key":"ref32","first-page":"1","article-title":"Improved variational inference with inverse autoregressive flow","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Kingma","year":"2016"},{"key":"ref33","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rezende","year":"2015"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972726.14"},{"key":"ref35","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017"},{"key":"ref36","first-page":"552","article-title":"Deep mixture of experts via shallow embedding","volume-title":"Proc. Uncertainty in AI","author":"Wang","year":"2020"},{"key":"ref37","first-page":"5547","article-title":"GLaM: Efficient scaling of language models with mixture-of-experts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Du","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.407"},{"key":"ref39","first-page":"18332","article-title":"DeepSpeed-MoE: Advancing mixture-of-experts inference and training to power next-generation AI scale","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rajbhandari","year":"2022"},{"key":"ref40","first-page":"7103","article-title":"Mixture-of-experts with expert choice routing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zhou","year":"2022"},{"key":"ref41","first-page":"34600","article-title":"On the representation collapse of sparse mixture of experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Chi","year":"2022"},{"key":"ref42","first-page":"23049","article-title":"Towards understanding the mixture-of-experts layer in deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Chen","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2200299"},{"key":"ref44","article-title":"Resolving interference when merging models","author":"Yadav","year":"2023"},{"key":"ref45","first-page":"17703","article-title":"Merging models with fisher-weighted averaging","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Matena","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.254"},{"key":"ref47","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref48","article-title":"Editing models with task arithmetic","author":"Ilharco","year":"2022"},{"key":"ref49","article-title":"Language models are super mario: Absorbing abilities from homologous models as a free lunch","author":"Yu","year":"2023"},{"key":"ref50","article-title":"Knowledge fusion of large language models","author":"Wan","year":"2024"},{"key":"ref51","article-title":"Git re-basin: Merging models modulo permutation symmetries","author":"Ainsworth","year":"2022"},{"key":"ref52","first-page":"21696","article-title":"Variational diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Kingma","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-31438-4_12"},{"key":"ref54","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020"},{"key":"ref55","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref56","first-page":"1","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Song","year":"2019"},{"key":"ref57","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref58","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref59","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Saharia","year":"2022"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref61","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref62","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed","year":"2016"},{"key":"ref63","article-title":"Midjourney","year":"2024"},{"key":"ref64","first-page":"1","article-title":"Multimodal generative models for scalable weakly-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Wu","year":"2018"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2022.2035253"},{"key":"ref66","article-title":"Variational mixture-of-experts autoencoders for multi-modal deep generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Shi","year":"2019"},{"key":"ref67","first-page":"689","article-title":"Multimodal deep learning","volume-title":"Proc. 28th Int. Conf. Mach. Learn. (ICML-11)","author":"Ngiam","year":"2011"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref69","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref70","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref74","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref75","article-title":"Sora: OpenAI\u2019s platform for multimodal AI","year":"2024"},{"key":"ref76","article-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref77","article-title":"An overview of Bard: An early experiment with generative AI","volume-title":"AI. Google Static Documents","author":"Manyika","year":"2024"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrm.2022.100794"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.6b00367"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1021\/acs.molpharmaceut.6b00248"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06735-9"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1557\/mrs.2019.158"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-022-00765-z"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1080\/01605682.2021.1880296"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-59050-9_12"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.01.010"},{"key":"ref87","first-page":"1052","article-title":"Generative adversarial user model for reinforcement learning based recommendation system","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2019"},{"key":"ref88","article-title":"Towards a human-like open-domain chatbot","author":"Adiwardana","year":"2020"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.21236\/ADA440321"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2006.06.006"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2000.0149"},{"key":"ref92","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref93","article-title":"Searching for activation functions","author":"Ramachandran","year":"2017"},{"issue":"8","key":"ref94","first-page":"p. 9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref95","article-title":"Scaling language models: Methods, analysis & insights from training gopher","author":"Rae","year":"2021"},{"key":"ref96","article-title":"Jurassic-1: Technical details and evaluation","volume":"1","author":"Lieber","year":"2021","journal-title":"White Paper. AI21 Labs"},{"key":"ref97","article-title":"Using DeepSpeed and megatron to train megatron-turing NLG 530B, a large-scale generative language model","author":"Smith","year":"2022"},{"key":"ref98","article-title":"Training compute-optimal large language models","author":"Hoffmann","year":"2022"},{"key":"ref99","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ouyang","year":"2022"},{"key":"ref100","article-title":"Pathways language model (PaLM): Scaling to 540 billion parameters for breakthrough performance","volume-title":"Google AI Blog","author":"Narang","year":"2024"},{"key":"ref101","article-title":"PaLM: Scaling language modeling with pathways","author":"Chowdhery","year":"2022"},{"key":"ref102","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref103","article-title":"PaLM 2 technical report","author":"Anil","year":"2023"},{"key":"ref104","article-title":"GPT-4 Technical Report","year":"2023"},{"key":"ref105","article-title":"Gemini: A family of highly capable multimodal models","year":"Google"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v38i4.2745"},{"key":"ref107","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/945645.945658"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3045"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.249"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"},{"key":"ref113","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zaheer","year":"2020"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref115","first-page":"1","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yang","year":"2019"},{"key":"ref116","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020"},{"key":"ref117","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1223"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00065"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref123","article-title":"Exploring the limits of language modeling","author":"Jozefowicz","year":"2016"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682850"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682539"},{"key":"ref126","first-page":"p. 1","article-title":"Abstractive summarization using attentive neural techniques","volume-title":"Proc. 15th Int. Conf. Natural Lang. Process.","author":"Krantz","year":"2018"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1108\/ws.2000.07949fab.004"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330699"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"ref130","article-title":"CodeXGLUE: A machine learning benchmark dataset for code understanding and generation","author":"Lu","year":"2021"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622525"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00404"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.302"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.7"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278779"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.399"},{"issue":"8","key":"ref137","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3546577","article-title":"Post-hoc interpretability for neural NLP: A survey","volume":"55","author":"Madsen","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"ref138","article-title":"Are large language models post hoc explainers?","author":"Kroeger","year":"2023"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1213"},{"key":"ref140","first-page":"17236","article-title":"Co-tuning for transfer learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"You","year":"2020"},{"key":"ref141","first-page":"12647","article-title":"ELASTIC: Numerical reasoning with adaptive symbolic compiler","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zhang","year":"2022"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00517"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01155"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813687"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-021-09563-w"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1007\/s43681-020-00002-7"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i09.7123"},{"key":"ref149","article-title":"AWQ: Activation-aware weight quantization for LLM compression and acceleration","author":"Lin","year":"2023"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.06.014"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.262"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.537"},{"key":"ref153","article-title":"The malicious use of artificial intelligence: Forecasting, prevention, and mitigation","author":"Brundage","year":"2018"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2870052"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v35i4.2513"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10246-w"},{"key":"ref157","first-page":"1","article-title":"Policy shaping: Integrating human feedback with reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Griffith","year":"2013"},{"key":"ref158","first-page":"2285","article-title":"Interactive learning from policy-dependent human feedback","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"MacGlashan","year":"2017"},{"key":"ref159","article-title":"Direct preference optimization: Your language model is secretly a reward model","author":"Rafailov","year":"2023"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09408-y"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref162","article-title":"On the planning abilities of large language models\u2013A critical investigation","author":"Valmeekam","year":"2023"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n16-1174"},{"key":"ref164","first-page":"1","article-title":"Improving neural language models with a continuous cache","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Grave","year":"2016"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.352"},{"key":"ref166","article-title":"One model to learn them all","author":"Kaiser","year":"2017"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054419"},{"key":"ref168","article-title":"End-to-end memory networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Sukhbaatar","year":"2015"},{"key":"ref169","article-title":"LLEMMA: An open language model mathematics","author":"Azerbayev","year":"2023"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.753"},{"key":"ref171","article-title":"JudgeLM: Fine-tuned large language models are scalable judges","author":"Zhu","year":"2023"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/10794552\/10638808.pdf?arnumber=10638808","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:09:38Z","timestamp":1755911378000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10638808\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":171,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tai.2024.3444742","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}