{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:18:13Z","timestamp":1763191093817,"version":"3.45.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100009950","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228532","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Why Lift so Heavy? Slimming Large Language Models by Cutting Off the Layers"],"prefix":"10.1109","author":[{"given":"Shuzhou","family":"Yuan","sequence":"first","affiliation":[{"name":"ScaDS.AI and TU Dresden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ercong","family":"Nie","sequence":"additional","affiliation":[{"name":"LMU Munich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bolei","family":"Ma","sequence":"additional","affiliation":[{"name":"LMU Munich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"F\u00e4rber","sequence":"additional","affiliation":[{"name":"ScaDS.AI and TU Dresden"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Slicegpt: Compress large language models by deleting rows and columns","year":"2024","author":"Ashkboos","key":"ref1"},{"key":"ref2","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"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/s19-2005"},{"journal-title":"Lorashear: Efficient large language model structured pruning and knowledge recovery","year":"2023","author":"Chen","key":"ref4"},{"article-title":"Reducing transformer depth on demand with structured dropout","volume-title":"International Conference on Learning Representations","author":"Fan","key":"ref5"},{"key":"ref6","first-page":"10323","article-title":"Sparsegpt: Massive language models can be accurately pruned in one-shot","volume-title":"International Conference on Machine Learning","author":"Frantar"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.295"},{"article-title":"Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding","volume-title":"4th International Conference on Learning Representations, ICLR","author":"Han","key":"ref8"},{"key":"ref9","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proceedings of the 36th International Conference on Machine Learning. Proceedings of Machine Learning Research","volume":"97","author":"Houlsby"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.3115\/1072133.1072221","article-title":"Toward semantics-based answer pinpointing","volume-title":"Proceedings of the First International Conference on Human Language Technology Research","author":"Hovy"},{"journal-title":"How to train your (compressed) large language model","year":"2023","author":"Jha","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1445"},{"issue":"1989","key":"ref13","article-title":"Optimal brain damage","volume":"2","author":"LeCun","journal-title":"Advances in neural information processing systems"},{"journal-title":"What would elsa do? freezing layers during transformer fine-tuning","year":"2019","author":"Lee","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.3115\/1072228.1072378","article-title":"Learning question classifiers","volume-title":"COLING 2002: The 19th International Conference on Computational Linguistics","author":"Li"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1112"},{"article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov","key":"ref19"},{"key":"ref20","first-page":"1","article-title":"Is prompt-based finetuning always better than vanilla finetuning? insights from cross-lingual language understanding","volume-title":"Proceedings of the 19th Conference on Natural Language Processing (KONVENS 2023)","author":"Ma"},{"key":"ref21","first-page":"2685","article-title":"ToPro: Token-level prompt decomposition for cross-lingual sequence labeling tasks","volume-title":"Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Ma"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2022.03.023"},{"issue":"8","key":"ref23","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2022.101429"},{"key":"ref25","first-page":"20378","article-title":"Movement pruning: Adaptive sparsity by fine-tuning","volume":"33","author":"Sanh","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.185"},{"key":"ref28","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","volume-title":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","author":"Socher"},{"article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.157"},{"key":"ref32","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"article-title":"Sheared llama: Accelerating language model pre-training via structured pruning","volume-title":"Workshop on Advancing Neural Network Training: Computational Efficiency, Scalability, and Resource Optimization (WANT@ NeurIPS 2023)","author":"Xia","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.107"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.188"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.findings-acl.237","article-title":"Gnnavi: Navigating the information flow in large language models by graph neural network","volume-title":"Findings of the Association for Computational Linguistics: ACL 2024","author":"Yuan"},{"article-title":"Opt: Open pre-trained transformer language models","year":"2022","author":"Zhang","key":"ref38"},{"key":"ref39","article-title":"Character-level convolutional networks for text classification","volume-title":"Advances in Neural Information Processing Systems","volume":"28","author":"Zhang","year":"2015"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228532.pdf?arnumber=11228532","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:14:47Z","timestamp":1763190887000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228532\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228532","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}