{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T05:57:36Z","timestamp":1763704656228,"version":"3.45.0"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,26]]},"DOI":"10.1109\/iccad66269.2025.11240962","type":"proceedings-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T18:39:34Z","timestamp":1763663974000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["TOGGLE: Temporal Logic-Guided Large Language Model Compression for Edge"],"prefix":"10.1109","author":[{"given":"Khurram","family":"Khalil","sequence":"first","affiliation":[{"name":"University of Missouri,Department of Electrical Engineering and Computer Science,Columbia,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khaza Anuarul","family":"Hoque","sequence":"additional","affiliation":[{"name":"University of Missouri,Department of Electrical Engineering and Computer Science,Columbia,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Palm: Scaling language modeling with pathways","year":"2022","author":"Chowdhery","key":"ref2"},{"article-title":"Using deepspeed and megatron to train megatronturing nlg 530b, a large-scale generative language model","year":"2022","author":"Smith","key":"ref3"},{"article-title":"Deepseek llm: Scaling open-source language models with longtermism","year":"2024","author":"D.-A","key":"ref4"},{"issue":"3","key":"ref5","first-page":"1","article-title":"Efficient edge deployment of compressed llms","volume":"6","author":"Zhou","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"article-title":"Llm.int8(): 8-bit matrix multiplication for transformers at scale","year":"2022","author":"Dettmers","key":"ref6"},{"article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","year":"2023","author":"Xiao","key":"ref7"},{"article-title":"Sparsegpt: Efficient pruning for large language models","year":"2023","author":"Frantar","key":"ref8"},{"article-title":"Sparse transformer architectures: Balancing efficiency and performance","volume-title":"Proceedings of the 2023 International Conference on Learning Representations","author":"Ma","key":"ref9"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref10"},{"key":"ref11","first-page":"456","article-title":"Compressing large language models for edge deployment: Challenges and opportunities","volume-title":"Proceedings of the 2023 International Conference on Edge Computing","author":"Gupta"},{"article-title":"Compression of large language models using reinforcement learning","year":"2023","author":"Yao","key":"ref12"},{"key":"ref13","first-page":"1234","article-title":"Bayesian optimization for neural network compression","volume-title":"Proceedings of the 2023 AAAI Conference on Artificial Intelligence","author":"Chen"},{"issue":"1","key":"ref14","first-page":"1","article-title":"Coherence in large language models: Challenges and solutions","volume":"24","author":"Liu","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref15","first-page":"1234","article-title":"Contextual consistency in multi-turn dialogues: A study on large language models","volume-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","author":"Henderson"},{"issue":"2","key":"ref16","first-page":"1","article-title":"Factual accuracy in large language models: A systematic evaluation","volume":"5","author":"Lin","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref17","article-title":"Layer-wise sensitivity analysis for transformer-based models","volume":"35","author":"Lin","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15297-9_9"},{"article-title":"On the opportunities and risks of foundation models","year":"2021","author":"Bommasani","key":"ref19"},{"key":"ref20","article-title":"Language models are unsupervised multitask learners","volume-title":"OpenAI Blog","author":"Radford","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref24","first-page":"3456","article-title":"Faithful or extractive? on mitigating the faithfulness-abstractiveness trade-off in abstractive summarization","volume-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","author":"Zhang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3578938"},{"article-title":"Training compute-optimal large language models","year":"2022","author":"Hoffmann","key":"ref26"},{"article-title":"Rtamt: Online robustness monitors from stl","year":"2020","author":"Nickovic","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30206-3_12"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2832544"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-75632-5_5"},{"article-title":"Learned step size quantization","year":"2020","author":"Esser","key":"ref31"},{"article-title":"Paretoq: Scaling laws in extremely low-bit llm quantization","year":"2025","author":"Liu","key":"ref32"},{"article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","volume-title":"International Conference on Learning Representations (ICLR)","author":"Han","key":"ref33"},{"article-title":"The state of sparsity in deep neural networks","year":"2019","author":"Gale","key":"ref34"},{"article-title":"Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks","year":"2021","author":"Hoefler","key":"ref35"},{"key":"ref36","first-page":"2951","article-title":"Practical bayesian optimization of machine learning algorithms","volume":"25","author":"Snoek","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","first-page":"937","article-title":"Bayesian optimization with inequality constraints","volume-title":"Proceedings of the 31st International Conference on Machine Learning (ICML)","volume":"32","author":"Gardner"},{"year":"2024","key":"ref38","article-title":"Deepseek-v2: A strong, economical, and efficient mixture-of-experts language model"},{"article-title":"The llama 3 herd of models","year":"2024","author":"G","key":"ref39"},{"article-title":"Mistral 7b","year":"2023","author":"Jiang","key":"ref40"},{"key":"ref41","first-page":"1525","article-title":"The lambada dataset: Word prediction requiring a broad discourse context","volume":"1","author":"Paperno","year":"2016"},{"article-title":"Pointer sentinel mixture models","year":"2016","author":"Merity","key":"ref42"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2022.acl-long.229","article-title":"Truthfulqa: Measuring how models mimic human falsehoods","author":"Lin","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.23919\/DATE56975.2023.10136954"},{"key":"ref45","article-title":"BoTorch: A Framework for Efficient Monte-Carlo Bayesian Optimization","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Balandat","year":"2020"}],"event":{"name":"2025 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)","start":{"date-parts":[[2025,10,26]]},"location":"Munich, Germany","end":{"date-parts":[[2025,10,30]]}},"container-title":["2025 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11240608\/11240621\/11240962.pdf?arnumber=11240962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T05:47:20Z","timestamp":1763704040000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11240962\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,26]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iccad66269.2025.11240962","relation":{},"subject":[],"published":{"date-parts":[[2025,10,26]]}}}