{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:22:39Z","timestamp":1782994959055,"version":"3.54.5"},"reference-count":235,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T00:00:00Z","timestamp":1748044800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Softw. Eng. Methodol."],"published-print":{"date-parts":[[2025,6,30]]},"abstract":"<jats:p>When mobile meets LLMs, mobile app users deserve to have more intelligent usage experiences. For this to happen, we argue that there is a strong need to apply LLMs for the mobile ecosystem. We therefore provide a research roadmap for guiding our fellow researchers to achieve that as a whole. In this roadmap, we sum up six directions that we believe are urgently required for research to enable native intelligence in mobile devices. In each direction, we further summarize the current research progress and the gaps that still need to be filled by our fellow researchers.<\/jats:p>","DOI":"10.1145\/3708528","type":"journal-article","created":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T13:58:06Z","timestamp":1734703086000},"page":"1-29","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["LLM for Mobile: An Initial Roadmap"],"prefix":"10.1145","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0880-4317","authenticated-orcid":false,"given":"Daihang","family":"Chen","sequence":"first","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7548-5100","authenticated-orcid":false,"given":"Yonghui","family":"Liu","sequence":"additional","affiliation":[{"name":"Monash University, Clayton, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3514-0372","authenticated-orcid":false,"given":"Mingyi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8793-5367","authenticated-orcid":false,"given":"Yanjie","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1100-8633","authenticated-orcid":false,"given":"Haoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0866-0308","authenticated-orcid":false,"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of CSE, Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4224-6450","authenticated-orcid":false,"given":"Xiao","family":"Chen","sequence":"additional","affiliation":[{"name":"The University of Newcastle Australia, Callaghan, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7270-9869","authenticated-orcid":false,"given":"Tegawend\u00e9 F.","family":"Bissyand\u00e9","sequence":"additional","affiliation":[{"name":"University of Luxembourg, Esch-sur-Alzette, Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4052-475X","authenticated-orcid":false,"given":"Jacques","family":"Klein","sequence":"additional","affiliation":[{"name":"University of Luxembourg, Esch-sur-Alzette, Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2990-1614","authenticated-orcid":false,"given":"Li","family":"Li","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,5,24]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"NVIDIA Effective Transformer. 2020. Retrieved November 25 2023 from https:\/\/github.com\/NVIDIA\/FasterTransformer"},{"key":"e_1_3_2_3_2","unstructured":"FlexGen. 2023. Retrieved November 25 2023 from https:\/\/github.com\/FMInference\/FlexGen"},{"key":"e_1_3_2_4_2","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et al. 2023. Gpt-4 technical report. arXiv:2303.08774. Retrieved from https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME55016.2022.00020"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00073"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.20533\/jitst.2046.3723.2019.0077"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-49601-1_6"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3005348"},{"key":"e_1_3_2_10_2","first-page":"499","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201920)","author":"Bai Zhihao","year":"2020","unstructured":"Zhihao Bai, Zhen Zhang, Yibo Zhu, and Xin Jin. 2020. PipeSwitch: Fast pipelined context switching for deep learning applications. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201920), 499\u2013514."},{"key":"e_1_3_2_11_2","unstructured":"Patrick Barei\u00df Beatriz Souza Marcelo d\u2019Amorim and Michael Pradel. 2022. Code generation tools (almost) for free? A study of few-shot pre-trained language models on code. arXiv:2206.01335. Retrieved from https:\/\/arxiv.org\/abs\/2206.01335"},{"key":"e_1_3_2_12_2","first-page":"515","volume-title":"28th USENIX Security Symposium (USENIX Security \u201919)","author":"Batina Lejla","year":"2019","unstructured":"Lejla Batina, Shivam Bhasin, Dirmanto Jap, and Stjepan Picek. 2019. CSINN: Reverse engineering of neural network architectures through electromagnetic side channel. In 28th USENIX Security Symposium (USENIX Security \u201919), 515\u2013532."},{"key":"e_1_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Alexander Borzunov Dmitry Baranchuk Tim Dettmers Max Ryabinin Younes Belkada Artem Chumachenko Pavel Samygin and Colin Raffel. 2022. Petals: Collaborative inference and fine-tuning of large models. arXiv:2209.01188. Retrieved from https:\/\/arxiv.org\/abs\/2209.01188","DOI":"10.18653\/v1\/2023.acl-demo.54"},{"key":"e_1_3_2_14_2","first-page":"36","article-title":"Distributed inference and fine-tuning of large language models over the Internet","author":"Borzunov Alexander","year":"2024","unstructured":"Alexander Borzunov, Max Ryabinin, Artem Chumachenko, Dmitry Baranchuk, Tim Dettmers, Younes Belkada, Pavel Samygin, and Colin A. Raffel. 2024. Distributed inference and fine-tuning of large language models over the Internet. In Advances in Neural Information Processing Systems, 36.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_15_2","unstructured":"Tom B. Brown. 2020. Language models are few-shot learners. arXiv:2005.14165. Retrieved from https:\/\/arxiv.org\/abs\/2005.14165"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3293882.3330564"},{"key":"e_1_3_2_17_2","unstructured":"Angelica Chen J\u00e9r\u00e9my Scheurer Tomasz Korbak Jon Ander Campos Jun Shern Chan Samuel R. Bowman Kyunghyun Cho and Ethan Perez. 2023. Improving code generation by training with natural language feedback. arXiv:2303.16749. Retrieved from https:\/\/arxiv.org\/abs\/2303.16749"},{"key":"e_1_3_2_18_2","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Ponde De Oliveira Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman et al. 2021. Evaluating large language models trained on code. arXiv:2107.03374. Retrieved from https:\/\/arxiv.org\/abs\/2107.03374"},{"key":"e_1_3_2_19_2","first-page":"578","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201918)","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, et al. 2018. TVM: An automated end-to-end optimizing compiler for deep learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201918), 578\u2013594."},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.02.037"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2023.24103"},{"key":"e_1_3_2_22_2","unstructured":"Yu Cheng Duo Wang Pan Zhou and Tao Zhang. 2017. A survey of model compression and acceleration for deep neural networks. arXiv:1710.09282. Retrieved from https:\/\/arxiv.org\/abs\/1710.09282"},{"key":"e_1_3_2_23_2","unstructured":"Wei-Lin Chiang Zhuohan Li Zi Lin Ying Sheng Zhanghao Wu Hao Zhang Lianmin Zheng Siyuan Zhuang Yonghao Zhuang Joseph E. Gonzalez et al. 2023. Vicuna: An open-source chatbot impressing GPT-4 with 90%* ChatGPT quality. Retrieved April 14 2023 from https:\/\/vicuna.lmsys.org"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME55016.2022.00080"},{"issue":"240","key":"e_1_3_2_25_2","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery Aakanksha","year":"2023","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. 2023. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research 24, 240 (2023), 1\u2013113.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_26_2","unstructured":"Christian Collberg Clark Thomborson and Douglas Low. 1997. A taxonomy of obfuscating transformations."},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/268946.268962"},{"key":"e_1_3_2_28_2","first-page":"800","volume-title":"Proceedings of Machine Learning and Systems","volume":"3","author":"David Robert","year":"2021","unstructured":"Robert David, Jared Duke, Advait Jain, Vijay Janapa Reddi, Nat Jeffries, Jian Li, Nick Kreeger, Ian Nappier, Meghna Natraj, Tiezhen Wang, et al. 2021. TensorFlow Lite Micro: Embedded machine learning for TinyML systems. Proceedings of Machine Learning and Systems 3 (2021), 800\u2013811."},{"key":"e_1_3_2_29_2","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805. Retrieved from https:\/\/arxiv.org\/abs\/1810.04805"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"e_1_3_2_31_2","unstructured":"Shihan Dou Junjie Shan Haoxiang Jia Wenhao Deng Zhiheng Xi Wei He Yueming Wu Tao Gui Yang Liu and Xuanjing Huang. 2023. Towards understanding the capability of large language models on code clone detection: A survey. arXiv:2308.01191. Retrieved from https:\/\/arxiv.org\/abs\/2308.01191"},{"key":"e_1_3_2_32_2","unstructured":"Darren Edge Ha Trinh Newman Cheng Joshua Bradley Alex Chao Apurva Mody Steven Truitt and Jonathan Larson. 2024. From local to global: A graph RAG approach to query-focused summarization. arXiv:2404.16130. Retrieved from https:\/\/arxiv.org\/abs\/2404.16130"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510157"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-FoSE59343.2023.00008"},{"key":"e_1_3_2_35_2","unstructured":"Angela Fan Mike Lewis and Yann Dauphin. 2018. Hierarchical neural story generation. arXiv:1805.04833. Retrieved from https:\/\/arxiv.org\/abs\/1805.04833"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01544"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_5"},{"issue":"120","key":"e_1_3_2_38_2","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus William","year":"2022","unstructured":"William Fedus, Barret Zoph, and Noam Shazeer. 2022. Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. Journal of Machine Learning Research 23, 120 (2022), 1\u201339.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00148"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"e_1_3_2_41_2","unstructured":"FlowiseAI. 2024. FlowiseAI - Build LLM Apps Easily. Retrieved January 2 2025 from https:\/\/flowiseai.com\/"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2019.00065"},{"key":"e_1_3_2_43_2","unstructured":"Yunfan Gao Yun Xiong Xinyu Gao Kangxiang Jia Jinliu Pan Yuxi Bi Yi Dai Jiawei Sun and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey. arXiv:2312.10997. Retrieved from https:\/\/arxiv.org\/abs\/2312.10997"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2021.106566"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"key":"e_1_3_2_46_2","doi-asserted-by":"crossref","unstructured":"Henry Gilbert Michael Sandborn Douglas C. Schmidt Jesse Spencer-Smith and Jules White. 2023. Semantic compression with large language models. arXiv:2304.12512. Retrieved from https:\/\/arxiv.org\/abs\/2304.12512","DOI":"10.1109\/SNAMS60348.2023.10375400"},{"key":"e_1_3_2_47_2","doi-asserted-by":"crossref","unstructured":"Mitchell A. Gordon Kevin Duh and Nicholas Andrews. 2020. Compressing BERT: Studying the effects of weight pruning on transfer learning. arXiv:2002.08307. Retrieved from https:\/\/arxiv.org\/abs\/2002.08307","DOI":"10.18653\/v1\/2020.repl4nlp-1.18"},{"key":"e_1_3_2_48_2","unstructured":"GradientJ. 2024. GradientJ - Everything You Need to Build LLM Native Applications. Retrieved January 2 2025 from https:\/\/www.gradientj.com\/"},{"key":"e_1_3_2_49_2","unstructured":"Giovanni Grano Andrea Di Sorbo Francesco Mercaldo Corrado Aaron Visaggio Gerardo Canfora and Sebastiano Panichella. 2017. Software Applications User Reviews. Retrieved from https:\/\/huggingface.co\/datasets\/sealuzh\/app_reviews"},{"key":"e_1_3_2_50_2","unstructured":"Siqi Gu Chunrong Fang Quanjun Zhang Fangyuan Tian and Zhenyu Chen. 2024. TestART: Improving LLM-based unit test via co-evolution of automated generation and repair iteration. arXiv:2408.03095. Retrieved from https:\/\/arxiv.org\/abs\/2408.03095"},{"key":"e_1_3_2_51_2","first-page":"1041","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI \u201922)","author":"Gunasekaran Jashwant Raj","year":"2022","unstructured":"Jashwant Raj Gunasekaran, Cyan Subhra Mishra, Prashanth Thinakaran, Bikash Sharma, Mahmut Taylan Kandemir, and Chita R. Das. 2022. Cocktail: A multidimensional optimization for model serving in cloud. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI \u201922), 1041\u20131057."},{"key":"e_1_3_2_52_2","unstructured":"Tom Gunter Zirui Wang Chong Wang Ruoming Pang Andy Narayanan Aonan Zhang Bowen Zhang Chen Chen Chung-Cheng Chiu David Qiu et al. 2024. Apple intelligence foundation language models. arXiv:2407.21075. Retrieved from https:\/\/arxiv.org\/abs\/2407.21075"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623306"},{"key":"e_1_3_2_54_2","first-page":"3887","volume-title":"International Conference on Machine Learning","author":"Guo Ruiqi","year":"2020","unstructured":"Ruiqi Guo, Philip Sun, Erik Lindgren, Quan Geng, David Simcha, Felix Chern, and Sanjiv Kumar. 2020. Accelerating large-scale inference with anisotropic vector quantization. In International Conference on Machine Learning. PMLR, 3887\u20133896."},{"key":"e_1_3_2_55_2","doi-asserted-by":"crossref","unstructured":"Suchin Gururangan Ana Marasovi\u0107 Swabha Swayamdipta Kyle Lo Iz Beltagy Doug Downey and Noah A. Smith. 2020. Don\u2019t stop pretraining: Adapt language models to domains and tasks. arXiv:2004.10964. Retrieved from https:\/\/arxiv.org\/abs\/2004.10964","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"e_1_3_2_56_2","unstructured":"Muhammad Usman Hadi Qasem Al Tashi Rizwan Qureshi Abbas Shah Muhammad Irfan Anas Zafar Muhammad Bilal Shaikh Naveed Akhtar Syed Zohaib Hassan Maged Shoman et al. 2023. A survey on large language models: Applications challenges limitations and practical usage. Authorea Preprints (2023)."},{"key":"e_1_3_2_57_2","unstructured":"Aamir Hamid Hemanth Reddy Samidi Tim Finin Primal Pappachan and Roberto Yus. 2023. A study of the landscape of privacy policies of smart devices. arXiv:2308.05890. Retrieved from https:\/\/arxiv.org\/abs\/2308.05890"},{"key":"e_1_3_2_58_2","first-page":"539","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201922)","author":"Han Mingcong","year":"2022","unstructured":"Mingcong Han, Hanze Zhang, Rong Chen, and Haibo Chen. 2022. Microsecond-scale preemption for concurrent GPU-acceleratedDNN inferences. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201922), 539\u2013558."},{"key":"e_1_3_2_59_2","first-page":"28","article-title":"Learning both weights and connections for efficient neural network","author":"Han Song","year":"2015","unstructured":"Song Han, Jeff Pool, John Tran, and William Dally. 2015. Learning both weights and connections for efficient neural network. In Advances in Neural Information Processing Systems, 28.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_60_2","unstructured":"Zeyu Han Chao Gao Jinyang Liu Jeff Zhang and Sai Qian Zhang. 2024. Parameter-efficient fine-tuning for large models: A comprehensive survey. arXiv:2403.14608. Retrieved from https:\/\/arxiv.org\/abs\/2403.14608"},{"key":"e_1_3_2_61_2","unstructured":"Yu Hao Weiteng Chen Ziqiao Zhou and Weidong Cui. 2023. E&V: Prompting large language models to perform static analysis by pseudo-code execution and verification. arXiv:2312.08477. Retrieved from https:\/\/arxiv.org\/abs\/2312.08477"},{"key":"e_1_3_2_62_2","first-page":"194 194","volume-title":"Leibniz International Proceedings in Informatics","author":"Hao Yu","year":"2021","unstructured":"Yu Hao, Sufian Latif, Hailong Zhang, Raef Bassily, and Atanas Rountev. 2021. Differential privacy for coverage analysis of software traces. Leibniz International Proceedings in Informatics 194 (2021), 194."},{"key":"e_1_3_2_63_2","unstructured":"Geoffrey Hinton. 2015. Distilling the knowledge in a neural network. arXiv:1503.02531. Retrieved from https:\/\/arxiv.org\/abs\/1503.02531"},{"key":"e_1_3_2_64_2","first-page":"497","volume-title":"28th USENIX Security Symposium (USENIX Security \u201919)","author":"Hong Sanghyun","year":"2019","unstructured":"Sanghyun Hong, Pietro Frigo, Yi\u011fitcan Kaya, Cristiano Giuffrida, and Tudor Dumitras\u0328. 2019. Terminal brain damage: Exposing the graceless degradation in deep neural networks under hardware fault attacks. In 28th USENIX Security Symposium (USENIX Security \u201919), 497\u2013514."},{"key":"e_1_3_2_65_2","unstructured":"Xinying Hou Yanjie Zhao Yue Liu Zhou Yang Kailong Wang Li Li Xiapu Luo David Lo John C. Grundy and Haoyu Wang. 2023. Large language models for software engineering: A systematic literature review. arXiv:2308.10620. Retrieved from https:\/\/api.semanticscholar.org\/CorpusID:261048648"},{"key":"e_1_3_2_66_2","unstructured":"Edward J. Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2021. LoRA: Low-rank adaptation of large language models. arXiv:2106.09685. Retrieved from https:\/\/arxiv.org\/abs\/2106.09685"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2019.2908939"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238191"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/tifs.2022.3172213"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623298"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00807"},{"key":"e_1_3_2_72_2","doi-asserted-by":"crossref","unstructured":"Akshath Jain David Rodriguez Jose M. del Alamo and Norman Sadeh. 2023. ATLAS: Automatically detecting discrepancies between privacy policies and privacy labels. arXiv:2306.09247. Retrieved from https:\/\/arxiv.org\/abs\/2306.09247","DOI":"10.1109\/EuroSPW59978.2023.00016"},{"key":"e_1_3_2_73_2","doi-asserted-by":"crossref","unstructured":"Soyeong Jeong Jinheon Baek Sukmin Cho Sung Ju Hwang and Jong C. Park. 2024. Adaptive-RAG: Learning to adapt retrieval-augmented large language models through question complexity. arXiv:2403.14403. Retrieved from https:\/\/arxiv.org\/abs\/2403.14403","DOI":"10.18653\/v1\/2024.naacl-long.389"},{"key":"e_1_3_2_74_2","unstructured":"Nan Jiang Chengxiao Wang Kevin Liu Xiangzhe Xu Lin Tan and Xiangyu Zhang. 2023. Nova \\({}^{+}\\) : Generative language models for binaries. arXiv:2311.13721. Retrieved from https:\/\/arxiv.org\/abs\/2311.13721"},{"key":"e_1_3_2_75_2","unstructured":"Shuyang Jiang Yuhao Wang and Yu Wang. 2023. SelfEvolve: A code evolution framework via large language models. arXiv:2306.02907. Retrieved from https:\/\/arxiv.org\/abs\/2306.02907"},{"key":"e_1_3_2_76_2","unstructured":"Youhe Jiang Ran Yan Xiaozhe Yao Beidi Chen and Binhang Yuan. 2023. Hexgen: Generative inference of foundation model over heterogeneous decentralized environment. arXiv:2311.11514. Retrieved from https:\/\/arxiv.org\/abs\/2311.11514"},{"key":"e_1_3_2_77_2","doi-asserted-by":"crossref","unstructured":"Zhihan Jiang Jinyang Liu Zhuangbin Chen Yichen Li Junjie Huang Yintong Huo Pinjia He Jiazhen Gu and Michael R. Lyu. 2024. LILAC: Log parsing using LLMs with adaptive parsing cache. arXiv:2310.01796. Retrieved from https:\/\/arxiv.org\/abs\/2310.01796","DOI":"10.1145\/3643733"},{"key":"e_1_3_2_78_2","doi-asserted-by":"crossref","unstructured":"Xiaoqi Jiao Yichun Yin Lifeng Shang Xin Jiang Xiao Chen Linlin Li Fang Wang and Qun Liu. 2019. TinyBERT: Distilling BERT for natural language understanding. arXiv:1909.10351. Retrieved from https:\/\/arxiv.org\/abs\/1909.10351","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"e_1_3_2_79_2","unstructured":"Sungmin Kang Juyeon Yoon Nargiz Askarbekkyzy and Shin Yoo. 2023. Evaluating diverse large language models for automatic and general bug reproduction. arXiv:2311.04532. Retrieved from https:\/\/arxiv.org\/abs\/2311.04532"},{"key":"e_1_3_2_80_2","unstructured":"Sungmin Kang Juyeon Yoon and Shin Yoo. 2022. Large language models are few-shot testers: Exploring LLM-based general bug reproduction. arXiv:2209.11515. Retrieved from https:\/\/arxiv.org\/abs\/2209.11515"},{"key":"e_1_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00194"},{"key":"e_1_3_2_82_2","doi-asserted-by":"publisher","DOI":"10.1145\/3497776.3517770"},{"key":"e_1_3_2_83_2","doi-asserted-by":"crossref","unstructured":"Mohamad Khajezade Jie J. W. Wu Fatemeh Hendijani Fard Gema Rodr\u00edguez-P\u00e9rez and Mohamed Sami Shehata. 2024. Investigating the efficacy of large language models for code clone detection. arXiv:2401.13802. Retrieved from https:\/\/arxiv.org\/abs\/2401.13802","DOI":"10.1145\/3643916.3645030"},{"key":"e_1_3_2_84_2","first-page":"16237","volume-title":"International Conference on Machine Learning","author":"Khakhar Adam","year":"2023","unstructured":"Adam Khakhar, Stephen Mell, and Osbert Bastani. 2023. PAC prediction sets for large language models of code. In International Conference on Machine Learning. PMLR, 16237\u201316249."},{"key":"e_1_3_2_85_2","unstructured":"Minsoo Kim Sihwa Lee Sukjin Hong Du-Seong Chang and Jungwook Choi. 2022. Understanding and improving knowledge distillation for quantization-aware training of large transformer encoders. arXiv:2211.11014. Retrieved from https:\/\/arxiv.org\/abs\/2211.11014"},{"key":"e_1_3_2_86_2","doi-asserted-by":"crossref","unstructured":"Yoon Kim and Alexander M. Rush. 2016. Sequence-level knowledge distillation. arXiv:1606.07947. Retrieved from https:\/\/arxiv.org\/abs\/1606.07947","DOI":"10.18653\/v1\/D16-1139"},{"key":"e_1_3_2_87_2","unstructured":"Takashi Koide Naoki Fukushi Hiroki Nakano and Daiki Chiba. 2023. Detecting phishing sites using ChatGPT. arXiv:2306.05816. Retrieved from https:\/\/arxiv.org\/abs\/2306.05816"},{"key":"e_1_3_2_88_2","unstructured":"Aobo Kong Shiwan Zhao Hao Chen Qicheng Li Yong Qin Ruiqi Sun Xin Zhou Enzhi Wang and Xiaohang Dong. 2023. Better zero-shot reasoning with role-play prompting. arXiv:2308.07702. Retrieved from https:\/\/arxiv.org\/abs\/2308.07702"},{"key":"e_1_3_2_89_2","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2018.2865733"},{"key":"e_1_3_2_90_2","unstructured":"Bonan Kou Muhao Chen and Tianyi Zhang. 2023. Automated summarization of stack overflow posts. arXiv:2305.16680. Retrieved from https:\/\/arxiv.org\/abs\/2305.16680"},{"key":"e_1_3_2_91_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_92_2","unstructured":"LangChain. [n.d.]. LangChain: Applications That Can Reason. Powered by LangChain. Retrieved March 20 2024 from https:\/\/www.langchain.com\/"},{"key":"e_1_3_2_93_2","unstructured":"Chris Lattner Mehdi Amini Uday Bondhugula Albert Cohen Andy Davis Jacques Pienaar River Riddle Tatiana Shpeisman Nicolas Vasilache and Oleksandr Zinenko. 2020. MLIR: A compiler infrastructure for the end of Moore\u2019s law. arXiv:2002.11054. Retrieved from https:\/\/arxiv.org\/abs\/2002.11054"},{"key":"e_1_3_2_94_2","first-page":"2","article-title":"Optimal brain damage","author":"LeCun Yann","year":"1989","unstructured":"Yann LeCun, John Denker, and Sara Solla. 1989. Optimal brain damage. In Advances in Neural Information Processing Systems, 2.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_95_2","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387532"},{"key":"e_1_3_2_96_2","unstructured":"Benjamin Lefaudeux Francisco Massa Diana Liskovich Wenhan Xiong Vittorio Caggiano Sean Naren Min Xu Jieru Hu Marta Tintore Susan Zhang et al. 2022. Xformers: A modular and hackable transformer modelling library."},{"key":"e_1_3_2_97_2","doi-asserted-by":"crossref","unstructured":"Brian Lester Rami Al-Rfou and Noah Constant. 2021. The power of scale for parameter-efficient prompt tuning. arXiv:2104.08691. Retrieved from https:\/\/arxiv.org\/abs\/2104.08691","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"e_1_3_2_98_2","unstructured":"Hao Li Asim Kadav Igor Durdanovic Hanan Samet and Hans Peter Graf. 2016. Pruning filters for efficient convnets. arXiv:1608.08710. Retrieved from https:\/\/arxiv.org\/abs\/1608.08710"},{"key":"e_1_3_2_99_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2015.48"},{"key":"e_1_3_2_100_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2019.2901679"},{"key":"e_1_3_2_101_2","doi-asserted-by":"publisher","DOI":"10.1145\/2931037.2931044"},{"key":"e_1_3_2_102_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2017.04.001"},{"key":"e_1_3_2_103_2","doi-asserted-by":"publisher","DOI":"10.1145\/3213846.3213857"},{"key":"e_1_3_2_104_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-019-09764-z"},{"key":"e_1_3_2_105_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2017.2656460"},{"key":"e_1_3_2_106_2","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549099"},{"key":"e_1_3_2_107_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3030548"},{"key":"e_1_3_2_108_2","unstructured":"Tsz-On Li Wenxi Zong Yibo Wang Haoye Tian Ying Wang and Shing-Chi Cheung. 2023. Finding failure-inducing test cases with ChatGPT. arXiv:2304.11686. Retrieved from https:\/\/arxiv.org\/abs\/2304.11686"},{"key":"e_1_3_2_109_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00089"},{"key":"e_1_3_2_110_2","unstructured":"Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. arXiv:2101.00190. Retrieved from https:\/\/arxiv.org\/abs\/2101.00190"},{"key":"e_1_3_2_111_2","unstructured":"Yichen Li Yintong Huo Zhihan Jiang Renyi Zhong Pinjia He Yuxin Su and Michael R. Lyu. 2023. Exploring the effectiveness of LLMs in automated logging generation: An empirical study. arXiv:2307.05950. Retrieved from https:\/\/arxiv.org\/abs\/2307.05950"},{"key":"e_1_3_2_112_2","unstructured":"Zongjie Li Chaozheng Wang Zhibo Liu Haoxuan Wang Shuai Wang and Cuiyun Gao. 2022. CCTEST: Testing and repairing code completion systems. arXiv:2208.08289. Retrieved from https:\/\/arxiv.org\/abs\/2208.08289"},{"key":"e_1_3_2_113_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2014.2360674"},{"key":"e_1_3_2_114_2","unstructured":"Feng Lin Dong Jae Kim and Tse-Husn (Peter) Chen. 2024. When LLM-based code generation meets the software development process. arXiv:2403.15852. Retrieved from https:\/\/arxiv.org\/abs\/2403.15852"},{"key":"e_1_3_2_115_2","unstructured":"Zachary Chase Lipton. 2015. A critical review of recurrent neural networks for sequence learning. arXiv:1506.00019. Retrieved from https:\/\/arxiv.org\/abs\/1506.00019"},{"key":"e_1_3_2_116_2","unstructured":"Fang Liu Yang Liu Lin Shi Houkun Huang Ruifeng Wang Zhen Yang and Li Zhang. 2024. Exploring and evaluating hallucinations in LLM-powered code generation. arXiv:2404.00971. Retrieved from https:\/\/arxiv.org\/abs\/2404.00971"},{"key":"e_1_3_2_117_2","first-page":"1950","article-title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","author":"Liu Haokun","year":"2022","unstructured":"Haokun Liu, Derek Tam, Mohammed Muqeeth, Jay Mohta, Tenghao Huang, Mohit Bansal, and Colin A. Raffel. 2022. Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning. In Advances in Neural Information Processing Systems, 1950\u20131965.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_118_2","unstructured":"Jiawei Liu Chunqiu Steven Xia Yuyao Wang and Lingming Zhang. 2023. Is your code generated by ChatGPT really correct? Rigorous evaluation of large language models for code generation. arXiv:2305.01210. Retrieved from https:\/\/arxiv.org\/abs\/2305.01210"},{"key":"e_1_3_2_119_2","doi-asserted-by":"crossref","unstructured":"Xiao Liu Heyan Huang Ge Shi and Bo Wang. 2022. Dynamic prefix-tuning for generative template-based event extraction. arXiv:2205.06166. Retrieved from https:\/\/arxiv.org\/abs\/2205.06166","DOI":"10.18653\/v1\/2022.acl-long.358"},{"issue":"8","key":"e_1_3_2_120_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3544968","article-title":"Deep learning for Android malware defenses: A systematic literature review","volume":"55","author":"Liu Yue","year":"2022","unstructured":"Yue Liu, Chakkrit Tantithamthavorn, Li Li, and Yepang Liu. 2022. Deep learning for Android malware defenses: A systematic literature review. ACM Computing Survey 55, 8 (2022), 1\u201336.","journal-title":"ACM Computing Survey"},{"key":"e_1_3_2_121_2","doi-asserted-by":"publisher","DOI":"10.1145\/3641540"},{"key":"e_1_3_2_122_2","unstructured":"Zhe Liu Chunyang Chen Junjie Wang Xing Che Yuekai Huang Jun Hu and Qing Wang. 2022. Fill in the blank: Context-aware automated text input generation for mobile GUI testing. arXiv:2212.04732. Retrieved from https:\/\/arxiv.org\/abs\/2212.04732"},{"key":"e_1_3_2_123_2","first-page":"22137","volume-title":"International Conference on Machine Learning","author":"Liu Zichang","year":"2023","unstructured":"Zichang Liu, Jue Wang, Tri Dao, Tianyi Zhou, Binhang Yuan, Zhao Song, Anshumali Shrivastava, Ce Zhang, Yuandong Tian, Christopher Re, et al. 2023. Deja vu: Contextual sparsity for efficient LLMs at inference time. In International Conference on Machine Learning. PMLR, 22137\u201322176."},{"key":"e_1_3_2_124_2","first-page":"28092","article-title":"Post-training quantization for vision transformer","author":"Liu Zhenhua","year":"2021","unstructured":"Zhenhua Liu, Yunhe Wang, Kai Han, Wei Zhang, Siwei Ma, and Wen Gao. 2021. Post-training quantization for vision transformer. In Advances in Neural Information Processing Systems, 28092\u201328103.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_125_2","unstructured":"Zechun Liu Changsheng Zhao Forrest Iandola Chen Lai Yuandong Tian Igor Fedorov Yunyang Xiong Ernie Chang Yangyang Shi Raghuraman Krishnamoorthi et al. 2024. MobileLLM: Optimizing sub-billion parameter language models for on-device use cases. arXiv:2402.14905. Retrieved from https:\/\/arxiv.org\/abs\/2402.14905"},{"key":"e_1_3_2_126_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE59848.2023.00026"},{"key":"e_1_3_2_127_2","unstructured":"Kai Lv Yuqing Yang Tengxiao Liu Qinghui Gao Qipeng Guo and Xipeng Qiu. 2023. Full parameter fine-tuning for large language models with limited resources. arXiv:2306.09782. Retrieved from https:\/\/arxiv.org\/abs\/2306.09782"},{"key":"e_1_3_2_128_2","doi-asserted-by":"crossref","unstructured":"Rabeeh Karimi Mahabadi Sebastian Ruder Mostafa Dehghani and James Henderson. 2021. Parameter-efficient multi-task fine-tuning for transformers via shared hypernetworks. arXiv:2106.04489. Retrieved from https:\/\/arxiv.org\/abs\/2106.04489","DOI":"10.18653\/v1\/2021.acl-long.47"},{"key":"e_1_3_2_129_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3511561"},{"key":"e_1_3_2_130_2","volume-title":"Workshop on Efficient Systems for Foundation Models II@ (ICML \u201924)","author":"Mehta Sachin","year":"2024","unstructured":"Sachin Mehta, Mohammad Hossein Sekhavat, Qingqing Cao, Maxwell Horton, Yanzi Jin, Chenfan Sun, Seyed Iman Mirzadeh, Mahyar Najibi, Dmitry Belenko, Peter Zatloukal, et al. 2024. OpenELM: An efficient language model family with open training and inference framework. In Workshop on Efficient Systems for Foundation Models II@ (ICML \u201924)."},{"key":"e_1_3_2_131_2","unstructured":"Xupeng Miao Gabriele Oliaro Zhihao Zhang Xinhao Cheng Zeyu Wang Rae Ying Yee Wong Zhuoming Chen Daiyaan Arfeen Reyna Abhyankar and Zhihao Jia. 2023. Specinfer: Accelerating generative LLM serving with speculative inference and token tree verification. arXiv:2305.09781. Retrieved from https:\/\/arxiv.org\/abs\/2305.09781"},{"key":"e_1_3_2_132_2","unstructured":"Shervin Minaee Tomas Mikolov Narjes Nikzad Meysam Chenaghlu Richard Socher Xavier Amatriain and Jianfeng Gao. 2024. Large language models: A survey. arXiv:2402.06196. Retrieved from https:\/\/arxiv.org\/abs\/2402.06196"},{"key":"e_1_3_2_133_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458864.3466628"},{"key":"e_1_3_2_134_2","doi-asserted-by":"publisher","DOI":"10.1145\/3386901.3388946"},{"key":"e_1_3_2_135_2","doi-asserted-by":"publisher","DOI":"10.1145\/3528588.3528651"},{"key":"e_1_3_2_136_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2019.2915318"},{"key":"e_1_3_2_137_2","first-page":"7197","volume-title":"International Conference on Machine Learning","author":"Nagel Markus","year":"2020","unstructured":"Markus Nagel, Rana Ali Amjad, Mart Van Baalen, Christos Louizos, and Tijmen Blankevoort. 2020. Up or down? Adaptive rounding for post-training quantization. In International Conference on Machine Learning. PMLR, 7197\u20137206."},{"key":"e_1_3_2_138_2","first-page":"7937","volume-title":"International Conference on Machine Learning","author":"Narayanan Deepak","year":"2021","unstructured":"Deepak Narayanan, Amar Phanishayee, Kaiyu Shi, Xie Chen, and Matei Zaharia. 2021. Memory-efficient pipeline-parallel DNN training. In International Conference on Machine Learning. PMLR, 7937\u20137947."},{"key":"e_1_3_2_139_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00065"},{"key":"e_1_3_2_140_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613163"},{"key":"e_1_3_2_141_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIS52602.2021.00012"},{"key":"e_1_3_2_142_2","unstructured":"Shidong Pan Zhen Tao Thong Hoang Dawen Zhang Zhenchang Xing Xiwei Xu Mark Staples and David Lo. 2023. SeePrivacy: Automated contextual privacy policy generation for mobile applications. arXiv:2307.01691. Retrieved from https:\/\/arxiv.org\/abs\/2307.01691"},{"key":"e_1_3_2_143_2","unstructured":"Baolin Peng Chunyuan Li Pengcheng He Michel Galley and Jianfeng Gao. 2023. Instruction tuning with GPT-4. arXiv:2304.03277. Retrieved from https:\/\/arxiv.org\/abs\/2304.03277"},{"key":"e_1_3_2_144_2","first-page":"606","volume-title":"Proceedings of Machine Learning and Systems","volume":"5","author":"Pope Reiner","year":"2023","unstructured":"Reiner Pope, Sholto Douglas, Aakanksha Chowdhery, Jacob Devlin, James Bradbury, Jonathan Heek, Kefan Xiao, Shivani Agrawal, and Jeff Dean. 2023. Efficiently scaling transformer inference. Proceedings of Machine Learning and Systems 5 (2023), 606\u2013624."},{"key":"e_1_3_2_145_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"e_1_3_2_146_2","unstructured":"Rohith Pudari and Neil A. Ernst. 2023. From copilot to pilot: Towards AI supported software development. arXiv:2303.04142. Retrieved from https:\/\/arxiv.org\/abs\/2303.04142"},{"key":"e_1_3_2_147_2","unstructured":"Alec Radford. 2018. Improving language understanding by generative pre-training. (2018)."},{"issue":"8","key":"e_1_3_2_148_2","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford Alec","year":"2019","unstructured":"Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI Blog 1, 8 (2019), 9.","journal-title":"OpenAI Blog"},{"key":"e_1_3_2_149_2","unstructured":"Mirza Masfiqur Rahman and Ashish Kundu. 2024. Code hallucination. arXiv:2407.04831. Retrieved from https:\/\/arxiv.org\/abs\/2407.04831"},{"key":"e_1_3_2_150_2","doi-asserted-by":"publisher","DOI":"10.1109\/sp46214.2022.9833743"},{"key":"e_1_3_2_151_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01321"},{"key":"e_1_3_2_152_2","first-page":"431","volume-title":"24th USENIX Security Symposium (USENIX Security \u201915)","author":"Rane Ashay","year":"2015","unstructured":"Ashay Rane, Calvin Lin, and Mohit Tiwari. 2015. Raccoon: Closing digital side-channels through obfuscated execution. In 24th USENIX Security Symposium (USENIX Security \u201915), 431\u2013446."},{"key":"e_1_3_2_153_2","unstructured":"Prakhar Rathi. 2019. Google Play Store Reviews. Retrieved from https:\/\/www.kaggle.com\/datasets\/prakharrathi25\/google-play-store-reviews"},{"key":"e_1_3_2_154_2","doi-asserted-by":"publisher","DOI":"10.1109\/Trustcom.2015.357"},{"key":"e_1_3_2_155_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510135"},{"key":"e_1_3_2_156_2","unstructured":"Victor Sanh L. Debut J. Chaumond and T. Wolf. 2019. DistilBERT a distilled version of BERT: Smaller faster cheaper and lighter. arXiv:1910.01108. Retrieved from https:\/\/arxiv.org\/abs\/1910.01108"},{"key":"e_1_3_2_157_2","doi-asserted-by":"publisher","DOI":"10.1145\/2886012"},{"key":"e_1_3_2_158_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER56733.2023.00049"},{"key":"e_1_3_2_159_2","unstructured":"Ying Sheng Shiyi Cao Dacheng Li Coleman Hooper Nicholas Lee Shuo Yang Christopher Chou Banghua Zhu Lianmin Zheng Kurt Keutzer et al. 2023. S-Lora: Serving thousands of concurrent Lora adapters. arXiv:2311.03285. Retrieved from https:\/\/arxiv.org\/abs\/2311.03285"},{"key":"e_1_3_2_160_2","first-page":"701","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201923)","author":"Shi Yining","year":"2023","unstructured":"Yining Shi, Zhi Yang, Jilong Xue, Lingxiao Ma, Yuqing Xia, Ziming Miao, Yuxiao Guo, Fan Yang, and Lidong Zhou. 2023. Welder: Scheduling deep learning memory access via tile-graph. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201923), 701\u2013718."},{"key":"e_1_3_2_161_2","unstructured":"Mohammad Shoeybi Mostofa Patwary Raul Puri Patrick LeGresley Jared Casper and Bryan Catanzaro. 2019. Megatron-LM: Training multi-billion parameter language models using model parallelism. arXiv:1909.08053. Retrieved from https:\/\/arxiv.org\/abs\/1909.08053"},{"key":"e_1_3_2_162_2","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813687"},{"key":"e_1_3_2_163_2","unstructured":"Mohammed Latif Siddiq Joanna Santos Ridwanul Hasan Tanvir Noshin Ulfat Fahmid Al Rifat and Vinicius Carvalho Lopes. 2023. Exploring the effectiveness of large language models in generating unit tests. arXiv:2305.00418. Retrieved from https:\/\/arxiv.org\/abs\/2305.00418"},{"key":"e_1_3_2_164_2","unstructured":"Yixin Song Zeyu Mi Haotong Xie and Haibo Chen. 2023. Powerinfer: Fast large language model serving with a consumer-grade GPU. arXiv:2312.12456. Retrieved from https:\/\/arxiv.org\/abs\/2312.12456"},{"key":"e_1_3_2_165_2","doi-asserted-by":"crossref","unstructured":"Siqi Sun Yu Cheng Zhe Gan and Jingjing Liu. 2019. Patient knowledge distillation for BERT model compression. arXiv:1908.09355. Retrieved from https:\/\/arxiv.org\/abs\/1908.09355","DOI":"10.18653\/v1\/D19-1441"},{"key":"e_1_3_2_166_2","unstructured":"Tiezhu Sun Kevin Allix Kisub Kim Xin Zhou Dongsun Kim David Lo Tegawend\u00e9 F. Bissyand\u00e9 and Jacques Klein. 2023. DexBERT: Effective task-agnostic and fine-grained representation learning of Android bytecode. arXiv:2212.05976. Retrieved from https:\/\/arxiv.org\/abs\/2212.05976"},{"key":"e_1_3_2_167_2","doi-asserted-by":"publisher","DOI":"10.1145\/3574158"},{"key":"e_1_3_2_168_2","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3561151"},{"key":"e_1_3_2_169_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510160"},{"key":"e_1_3_2_170_2","unstructured":"Shyam A. Tailor Javier Fernandez-Marques and Nicholas D. Lane. 2020. Degree-quant: Quantization-aware training for graph neural networks. arXiv:2008.05000. Retrieved from https:\/\/arxiv.org\/abs\/2008.05000"},{"key":"e_1_3_2_171_2","unstructured":"Feiyang Tang and Bjarte M. \u00d8stvold. 2023. User interaction data in apps: Comparing policy claims to implementations. arXiv:2312.02710. Retrieved from https:\/\/arxiv.org\/abs\/2312.02710"},{"key":"e_1_3_2_172_2","unstructured":"Rohan Taori Ishaan Gulrajani Tianyi Zhang Yann Dubois Xuechen Li Carlos Guestrin Percy Liang and Tatsunori B. Hashimoto. 2023. Stanford alpaca: An instruction-following LLaMa model."},{"key":"e_1_3_2_173_2","unstructured":"MLC Team. 2023. MLC-LLM. Retrieved November 25 2023 from https:\/\/github.com\/mlc-ai\/mlc-llm"},{"key":"e_1_3_2_174_2","unstructured":"Qwen Team. 2024. Qwen2.5: A Party of Foundation Models. Retrieved from https:\/\/qwenlm.github.io\/blog\/qwen2.5\/"},{"key":"e_1_3_2_175_2","unstructured":"Haoye Tian Weiqi Lu Tsz On Li Xunzhu Tang Shing-Chi Cheung Jacques Klein and Tegawend\u00e9 F. Bissyand\u00e9. 2023. Is ChatGPT the ultimate programming assistant\u2013How far is it? arXiv:2304.11938. Retrieved from https:\/\/arxiv.org\/abs\/2304.11938"},{"key":"e_1_3_2_176_2","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar et al. 2023. Llama: Open and efficient foundation language models. arXiv:2302.13971. Retrieved from https:\/\/arxiv.org\/abs\/2302.13971"},{"key":"e_1_3_2_177_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv:2307.09288. Retrieved from https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"e_1_3_2_178_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510621"},{"key":"e_1_3_2_179_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"e_1_3_2_180_2","unstructured":"Tim Valicenti Justice Vidal and Ritik Patnaik. 2023. Mini-GPTs: Efficient large language models through contextual pruning. arXiv:2312.12682. Retrieved from https:\/\/arxiv.org\/abs\/2312.12682"},{"key":"e_1_3_2_181_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-30921-2_10"},{"key":"e_1_3_2_182_2","doi-asserted-by":"crossref","unstructured":"Sameer Wagh Shruti Tople Fabrice Benhamouda Eyal Kushilevitz Prateek Mittal and Tal Rabin. 2020. Falcon: Honest-majority maliciously secure framework for private deep learning. arXiv:2004.02229. Retrieved from https:\/\/arxiv.org\/abs\/2004.02229","DOI":"10.2478\/popets-2021-0011"},{"key":"e_1_3_2_183_2","volume-title":"A Security Architecture for Survivability Mechanisms","author":"Wang Chenxi","year":"2001","unstructured":"Chenxi Wang. 2001. A Security Architecture for Survivability Mechanisms. University of Virginia."},{"key":"e_1_3_2_184_2","doi-asserted-by":"publisher","DOI":"10.1145\/3196398.3196412"},{"key":"e_1_3_2_185_2","doi-asserted-by":"publisher","DOI":"10.1145\/3278532.3278558"},{"key":"e_1_3_2_186_2","unstructured":"Junjie Wang Yuchao Huang Chunyang Chen Zhe Liu Song Wang and Qing Wang. 2024. Software testing with large language models: Survey landscape and vision. arXiv:2307.07221. Retrieved from https:\/\/arxiv.org\/abs\/2307.07221"},{"key":"e_1_3_2_187_2","unstructured":"Jian Wang Shangqing Liu Xiaofei Xie and Yi Li. 2023. Evaluating AIGC detectors on code content. arXiv:2304.05193. Retrieved from https:\/\/arxiv.org\/abs\/2304.05193"},{"key":"e_1_3_2_188_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367329"},{"key":"e_1_3_2_189_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00097"},{"key":"e_1_3_2_190_2","doi-asserted-by":"publisher","DOI":"10.1109\/RE48521.2020.00029"},{"key":"e_1_3_2_191_2","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"e_1_3_2_192_2","doi-asserted-by":"publisher","DOI":"10.1145\/3649856"},{"key":"e_1_3_2_193_2","unstructured":"Zekun Moore Wang Zhongyuan Peng Haoran Que Jiaheng Liu Wangchunshu Zhou Yuhan Wu Hongcheng Guo Ruitong Gan Zehao Ni Man Zhang et al. 2023. RoleLLM: Benchmarking eliciting and enhancing role-playing abilities of large language models. arXiv:2310.00746. Retrieved from https:\/\/arxiv.org\/abs\/2310.00746"},{"key":"e_1_3_2_194_2","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc V. Le, and Denny Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems, 24824\u201324837.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_195_2","doi-asserted-by":"publisher","DOI":"10.1109\/dsn48063.2020.00031"},{"key":"e_1_3_2_196_2","doi-asserted-by":"publisher","DOI":"10.1145\/3274694.3274696"},{"key":"e_1_3_2_197_2","first-page":"945","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI \u201922)","author":"Weng Qizhen","year":"2022","unstructured":"Qizhen Weng, Wencong Xiao, Yinghao Yu, Wei Wang, Cheng Wang, Jian He, Yong Li, Liping Zhang, Wei Lin, and Yu Ding. 2022. MLaaS in the wild: Workload analysis and scheduling in large-scale heterogeneous GPU clusters. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI \u201922), 945\u2013960."},{"key":"e_1_3_2_198_2","unstructured":"Wroblewski Gregory. 2002. General method of program code obfuscation. Ph. D. Thesis Wroclaw University of Technology Institute of Engineering Cybernetics."},{"key":"e_1_3_2_199_2","first-page":"795","volume-title":"6th Conference on Machine Translation","author":"Wu Kaixin","year":"2021","unstructured":"Kaixin Wu, Bojie Hu, and Qi Ju. 2021. TenTrans high-performance inference toolkit for WMT2021 efficiency task. In 6th Conference on Machine Translation, 795\u2013798."},{"key":"e_1_3_2_200_2","unstructured":"Yonghao Wu Zheng Li Jie M. Zhang Mike Papadakis Mark Harman and Yong Liu. 2023. Large language models in fault localisation. arXiv:2308.15276. Retrieved from https:\/\/arxiv.org\/abs\/2308.15276"},{"key":"e_1_3_2_201_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2020.2973007"},{"key":"e_1_3_2_202_2","unstructured":"Can Xu Qingfeng Sun Kai Zheng Xiubo Geng Pu Zhao Jiazhan Feng Chongyang Tao and Daxin Jiang. 2023. WizardLM: Empowering large language models to follow complex instructions. arXiv:2304.12244. Retrieved from https:\/\/arxiv.org\/abs\/2304.12244"},{"key":"e_1_3_2_203_2","doi-asserted-by":"publisher","DOI":"10.1145\/3638550.3641130"},{"key":"e_1_3_2_204_2","unstructured":"Mingxue Xu Yao Lei Xu and Danilo P. Mandic. 2023. TensorGPT: Efficient compression of the embedding layer in LLMs based on the tensor-train decomposition. arXiv:2307.00526. Retrieved from https:\/\/arxiv.org\/abs\/2307.00526"},{"key":"e_1_3_2_205_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3133824"},{"key":"e_1_3_2_206_2","unstructured":"An Yang Baosong Yang Binyuan Hui Bo Zheng Bowen Yu Chang Zhou Chengpeng Li Chengyuan Li Dayiheng Liu Fei Huang et al. 2024. Qwen2 technical report. arXiv:2407.10671. Retrieved from https:\/\/arxiv.org\/abs\/2407.10671"},{"key":"e_1_3_2_207_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623342"},{"key":"e_1_3_2_208_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER53432.2022.00054"},{"key":"e_1_3_2_209_2","doi-asserted-by":"publisher","DOI":"10.1109\/CSPA60979.2024.10525270"},{"key":"e_1_3_2_210_2","unstructured":"Juyeon Yoon Robert Feldt and Shin Yoo. 2023. Autonomous large language model agents enabling intent-driven mobile GUI testing. arXiv:2311.08649. Retrieved from https:\/\/arxiv.org\/abs\/2311.08649"},{"key":"e_1_3_2_211_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOST45689.2020.9300274"},{"key":"e_1_3_2_212_2","unstructured":"Ye Yuan Chengwu Liu Jingyang Yuan Gongbo Sun Siqi Li and Ming Zhang. 2024. A hybrid RAG system with comprehensive enhancement on complex reasoning. arXiv:2408.05141. Retrieved from https:\/\/arxiv.org\/abs\/2408.05141"},{"key":"e_1_3_2_213_2","unstructured":"Zhiqiang Yuan Yiling Lou Mingwei Liu Shiji Ding Kaixin Wang Yixuan Chen and Xin Peng. 2023. No more manual tests? Evaluating and improving ChatGPT for unit test generation. arXiv:2305.04207. Retrieved from https:\/\/arxiv.org\/abs\/2305.04207"},{"key":"e_1_3_2_214_2","doi-asserted-by":"publisher","DOI":"10.1145\/3533767.3534390"},{"key":"e_1_3_2_215_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS54959.2023.00042"},{"key":"e_1_3_2_216_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3114381"},{"key":"e_1_3_2_217_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01466"},{"key":"e_1_3_2_218_2","first-page":"1049","volume-title":"2019 USENIX Annual Technical Conference (USENIX ATC \u201919)","author":"Zhang Chengliang","year":"2019","unstructured":"Chengliang Zhang, Minchen Yu, Wei Wang, and Feng Yan. 2019. MArk: Exploiting cloud services for cost-effective, SLO-aware machine learning inference serving. In 2019 USENIX Annual Technical Conference (USENIX ATC \u201919), 1049\u20131062."},{"key":"e_1_3_2_219_2","doi-asserted-by":"publisher","DOI":"10.1145\/3196494.3196550"},{"key":"e_1_3_2_220_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2022.3227559"},{"key":"e_1_3_2_221_2","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3556955"},{"key":"e_1_3_2_222_2","unstructured":"Shengyu Zhang Linfeng Dong Xiaoya Li Sen Zhang Xiaofei Sun Shuhe Wang Jiwei Li Runyi Hu Tianwei Zhang Fei Wu et al. 2023. Instruction tuning for large language models: A survey. arXiv:2308.10792. Retrieved from https:\/\/arxiv.org\/abs\/2308.10792"},{"key":"e_1_3_2_223_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_12"},{"key":"e_1_3_2_224_2","unstructured":"Yue Zhang Yafu Li Leyang Cui Deng Cai Lemao Liu Tingchen Fu Xinting Huang Enbo Zhao Yu Zhang Yulong Chen et al. 2023. Siren\u2019s song in the AI ocean: A survey on hallucination in large language models. arXiv:2309.01219. Retrieved from https:\/\/arxiv.org\/abs\/2309.01219"},{"key":"e_1_3_2_225_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3106169"},{"key":"e_1_3_2_226_2","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A survey of large language models. arXiv:2303.18223. Retrieved from https:\/\/arxiv.org\/abs\/2303.18223"},{"key":"e_1_3_2_227_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510128"},{"key":"e_1_3_2_228_2","unstructured":"Lianmin Zheng Liangsheng Yin Zhiqiang Xie Jeff Huang Chuyue Sun Cody Hao Yu Shiyi Cao Christos Kozyrakis Ion Stoica Joseph E. Gonzalez et al. 2023. Efficiently programming large language models using SGLang. arXiv:2312.07104. Retrieved from https:\/\/arxiv.org\/abs\/2312.07104"},{"key":"e_1_3_2_229_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00392"},{"key":"e_1_3_2_230_2","doi-asserted-by":"crossref","unstructured":"Mingyi Zhou Xiang Gao Pei Liu John Grundy Chunyang Chen Xiao Chen and Li Li. 2024. Model-less is the best model: Generating pure code implementations to replace on-device DL models. arXiv:2403.16479. Retrieved from https:\/\/arxiv.org\/abs\/2403.16479","DOI":"10.1145\/3650212.3652119"},{"key":"e_1_3_2_231_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598113"},{"key":"e_1_3_2_232_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639144"},{"key":"e_1_3_2_233_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00031"},{"key":"e_1_3_2_234_2","unstructured":"Deyao Zhu Jun Chen Xiaoqian Shen Xiang Li and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv:2304.10592. Retrieved from https:\/\/arxiv.org\/abs\/2304.10592"},{"key":"e_1_3_2_235_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-023-10362-3"},{"key":"e_1_3_2_236_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586199"}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3708528","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3708528","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:46Z","timestamp":1750295866000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3708528"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,24]]},"references-count":235,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,6,30]]}},"alternative-id":["10.1145\/3708528"],"URL":"https:\/\/doi.org\/10.1145\/3708528","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"value":"1049-331X","type":"print"},{"value":"1557-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,24]]},"assertion":[{"value":"2024-04-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-05","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}