{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T10:11:40Z","timestamp":1783764700416,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T00:00:00Z","timestamp":1775952000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,12]]},"DOI":"10.1145\/3786583.3786896","type":"proceedings-article","created":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T09:12:14Z","timestamp":1783761134000},"page":"554-565","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Green LLM Techniques in Action: How Effective Are Existing Techniques for Improving the Energy Efficiency of LLM-Based Applications in Industry?"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0166-2569","authenticated-orcid":false,"given":"Pelin Rabia","family":"Kuran","sequence":"first","affiliation":[{"name":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0165-5650","authenticated-orcid":false,"given":"Rumbidzai","family":"Chitakunye","sequence":"additional","affiliation":[{"name":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3681-372X","authenticated-orcid":false,"given":"Vincenzo","family":"Stoico","sequence":"additional","affiliation":[{"name":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6589-3730","authenticated-orcid":false,"given":"Ilja","family":"Heitlager","sequence":"additional","affiliation":[{"name":"Schuberg Philis, Schiphol-Rijk, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5788-0991","authenticated-orcid":false,"given":"Justus","family":"Bogner","sequence":"additional","affiliation":[{"name":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,11]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Marah Abdin Jyoti Aneja Harkirat Behl S\u00e9bastien Bubeck Ronen Eldan Suriya Gunasekar Michael Harrison Russell\u00a0J. Hewett Mojan Javaheripi Piero Kauffmann James\u00a0R. Lee Yin\u00a0Tat Lee Yuanzhi Li Weishung Liu Caio C.\u00a0T. Mendes Anh Nguyen Eric Price Gustavo de Rosa Olli Saarikivi Adil Salim Shital Shah Xin Wang Rachel Ward Yue Wu Dingli Yu Cyril Zhang and Yi Zhang. 2024. Phi-4 Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2412.08905\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2412.08905"},{"key":"e_1_3_3_2_3_2","unstructured":"Marta Adamska Daria Smirnova Hamid Nasiri Zhengxin Yu and Peter Garraghan. 2025. Green Prompting. arxiv:https:\/\/arXiv.org\/abs\/2503.10666\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2503.10666"},{"key":"e_1_3_3_2_4_2","unstructured":"Eshaan Agarwal Joykirat Singh Vivek Dani Raghav Magazine Tanuja Ganu and Akshay Nambi. 2024. PromptWizard: Task-Aware Prompt Optimization Framework. arxiv:https:\/\/arXiv.org\/abs\/2405.18369\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2405.18369"},{"key":"e_1_3_3_2_5_2","unstructured":"Radu Apsan Vincenzo Stoico Michel Albonico Rudra Dhar Karthik Vaidhyanathan and Ivano Malavolta. 2025. Generating Energy-Efficient Code via Large-Language Models\u2013Where are we now? arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.10099 (2025)."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","unstructured":"Mauricio\u00a0Fadel Argerich and Marta Pati\u00f1o-Mart\u00ednez. 2024. Measuring and Improving the Energy Efficiency of Large Language Models Inference. IEEE Access 12 (2024) 80194\u201380207. 10.1109\/ACCESS.2024.3409745","DOI":"10.1109\/ACCESS.2024.3409745"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","unstructured":"Yupeng Chang Xu Wang Jindong Wang Yuan Wu Linyi Yang Kaijie Zhu Hao Chen Xiaoyuan Yi Cunxiang Wang Yidong Wang Wei Ye Yue Zhang Yi Chang Philip\u00a0S. Yu Qiang Yang and Xing Xie. 2024. A Survey on Evaluation of Large Language Models. ACM Transactions on Intelligent Systems and Technology 15 3 (June 2024) 1\u201345. 10.1145\/3641289","DOI":"10.1145\/3641289"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0196"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3604930.3605705"},{"key":"e_1_3_3_2_10_2","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano Christopher Hesse and John Schulman. 2021. Training Verifiers to Solve Math Word Problems. arxiv:https:\/\/arXiv.org\/abs\/2110.14168\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2110.14168"},{"key":"e_1_3_3_2_11_2","unstructured":"Francisco Dur\u00e1n Matias Martinez Patricia Lago and Silverio Mart\u00ednez-Fern\u00e1ndez. 2024. Energy consumption of code small language models serving with runtime engines and execution providers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.15441 (2024)."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC62300.2024.10737844"},{"key":"e_1_3_3_2_13_2","volume-title":"International Conference on Learning Representations","author":"Hendrycks Dan","unstructured":"Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. [n. d.]. Measuring Massive Multitask Language Understanding. In International Conference on Learning Representations."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Xinyi Hou Yanjie Zhao Yue Liu Zhou Yang Kailong Wang Li Li Xiapu Luo David Lo John Grundy and Haoyu Wang. 2024. Large Language Models for Software Engineering: A Systematic Literature Review. ACM Transactions on Software Engineering and Methodology (Sept. 2024) 3695988. 10.1145\/3695988","DOI":"10.1145\/3695988"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","unstructured":"Erik\u00a0Johannes Husom Arda Goknil Merve Astekin Lwin\u00a0Khin Shar Andre K\u00e5sen Sagar Sen Benedikt\u00a0Andreas Mithassel and Ahmet Soylu. 2025. Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency Output Accuracy and Inference Latency. ACM Trans. Internet Things (Sept. 2025). 10.1145\/3767742Just Accepted.","DOI":"10.1145\/3767742"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3639475.3640111"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCMC65190.2025.11140923"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Ishan Kavathekar Raghav Donakanti Ponnurangam Kumaraguru and Karthik Vaidhyanathan. 2025. Small models big tasks: An exploratory empirical study on small language models for function calling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.19277 (2025).","DOI":"10.1145\/3756681.3757001"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CAI64502.2025.00067"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1215"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Adam Loy Lendie Follett and Heike Hofmann. 2016. Variations of Q\u2013Q plots: The power of our eyes! The American Statistician 70 2 (2016) 202\u2013214.","DOI":"10.1080\/00031305.2015.1077728"},{"key":"e_1_3_3_2_22_2","unstructured":"Shuming Ma Hongyu Wang Shaohan Huang Xingxing Zhang Ying Hu Ting Song Yan Xia and Furu Wei. 2025. BitNet b1.58 2B4T Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2504.12285\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2504.12285"},{"key":"e_1_3_3_2_23_2","unstructured":"Shuming Ma Hongyu Wang Lingxiao Ma Lei Wang Wenhui Wang Shaohan Huang Li Dong Ruiping Wang Jilong Xue and Furu Wei. 2024. The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits. arxiv:https:\/\/arXiv.org\/abs\/2402.17764\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2402.17764"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"G. Macbeth E. Razumiejczyk and R.\u00a0D. Ledesma. 2011. Cliff\u2019s delta calculator: A non-parametric effect size program for two groups of observations. Universitas Psychologica 10 2 (2011) 545\u2013555.","DOI":"10.11144\/Javeriana.upsy10-2.cdcp"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-7962-2_30"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Patrick\u00a0E McKnight and Julius Najab. 2010. Mann-whitney U test. The Corsini encyclopedia of psychology (2010) 1\u20131.","DOI":"10.1002\/9780470479216.corpsy0524"},{"key":"e_1_3_3_2_27_2","unstructured":"Microsoft : Abdelrahman Abouelenin Atabak Ashfaq Adam Atkinson Hany Awadalla Nguyen Bach Jianmin Bao Alon Benhaim Martin Cai Vishrav Chaudhary Congcong Chen Dong Chen Dongdong Chen Junkun Chen Weizhu Chen Yen-Chun Chen Yi ling Chen Qi Dai Xiyang Dai Ruchao Fan Mei Gao Min Gao Amit Garg Abhishek Goswami Junheng Hao Amr Hendy Yuxuan Hu Xin Jin Mahmoud Khademi Dongwoo Kim Young\u00a0Jin Kim Gina Lee Jinyu Li Yunsheng Li Chen Liang Xihui Lin Zeqi Lin Mengchen Liu Yang Liu Gilsinia Lopez Chong Luo Piyush Madan Vadim Mazalov Arindam Mitra Ali Mousavi Anh Nguyen Jing Pan Daniel Perez-Becker Jacob Platin Thomas Portet Kai Qiu Bo Ren Liliang Ren Sambuddha Roy Ning Shang Yelong Shen Saksham Singhal Subhojit Som Xia Song Tetyana Sych Praneetha Vaddamanu Shuohang Wang Yiming Wang Zhenghao Wang Haibin Wu Haoran Xu Weijian Xu Yifan Yang Ziyi Yang Donghan Yu Ishmam Zabir Jianwen Zhang Li\u00a0Lyna Zhang Yunan Zhang and Xiren Zhou. 2025. Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs. arxiv:https:\/\/arXiv.org\/abs\/2503.01743\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2503.01743"},{"key":"e_1_3_3_2_28_2","unstructured":"Microsoft Azure. 2025. Pricing \u2013 Azure OpenAI Service. https:\/\/azure.microsoft.com\/en-us\/pricing\/details\/cognitive-services\/openai-service Accessed: 2025-06-30."},{"key":"e_1_3_3_2_29_2","unstructured":"Microsoft Azure. 2025. Pricing \u2013 Phi-3 Models. https:\/\/azure.microsoft.com\/en-us\/pricing\/details\/phi-3\/ Accessed: 2025-06-30."},{"key":"e_1_3_3_2_30_2","unstructured":"Avanika Narayan Dan Biderman Sabri Eyuboglu Avner May Scott Linderman James Zou and Christopher Re. 2025. Minions: Cost-efficient Collaboration Between On-device and Cloud Language Models. arxiv:https:\/\/arXiv.org\/abs\/2502.15964\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2502.15964"},{"key":"e_1_3_3_2_31_2","unstructured":"NVIDIA NeMo Curator Team. [n. d.]. Prompt Task and Complexity Classifier. https:\/\/huggingface.co\/nvidia\/prompt-task-and-complexity-classifier. Accessed: 2025-06-28."},{"key":"e_1_3_3_2_32_2","unstructured":"Rahul Pankajakshan Sumitra Biswal Yuvaraj Govindarajulu and Gilad Gressel. 2024. Mapping LLM Security Landscapes: A Comprehensive Stakeholder Risk Assessment Proposal. arxiv:https:\/\/arXiv.org\/abs\/2403.13309\u00a0[cs.CR] https:\/\/arxiv.org\/abs\/2403.13309"},{"key":"e_1_3_3_2_33_2","unstructured":"Soham Poddar Paramita Koley Janardan Misra Sanjay Podder Niloy Ganguly and Saptarshi Ghosh. 2025. Towards Sustainable NLP: Insights from Benchmarking Inference Energy in Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2502.05610\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2502.05610"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.432"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/GREENS66463.2025.00014"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","unstructured":"Per Runeson and Martin H\u00f6st. 2009. Guidelines for conducting and reporting case study research in software engineering. Empirical Software Engineering 14 2 (April 2009) 131\u2013164. 10.1007\/s10664-008-9102-8ISBN: 1382325615737616 _eprint: 9809069v1.","DOI":"10.1007\/s10664-008-9102-8"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","unstructured":"Roy Schwartz Jesse Dodge Noah\u00a0A. Smith and Oren Etzioni. 2020. Green AI. Commun. ACM 63 12 (Nov. 2020) 54\u201363. 10.1145\/3381831","DOI":"10.1145\/3381831"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"S.\u00a0S. Shapiro and M.\u00a0B. Wilk. 1965. An Analysis of Variance Test for Normality (Complete Samples). Biometrika 52 3\/4 (1965) 591\u2013611. http:\/\/www.jstor.org\/stable\/2333709","DOI":"10.1093\/biomet\/52.3-4.591"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00102"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-7563-6_53"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92734-8_22"},{"key":"e_1_3_3_2_42_2","unstructured":"Fali Wang Zhiwei Zhang Xianren Zhang Zongyu Wu Tzuhao Mo Qiuhao Lu Wanjing Wang Rui Li Junjie Xu Xianfeng Tang et\u00a0al. 2024. A comprehensive survey of small language models in the era of large language models: Techniques enhancements applications collaboration with llms and trustworthiness. ACM Transactions on Intelligent Systems and Technology (2024)."},{"key":"e_1_3_3_2_43_2","unstructured":"Eric\u00a0W Weisstein. 2004. Bonferroni correction. https:\/\/mathworld.wolfram.com\/ (2004)."},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-69306-3"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/SEAA60479.2023.00026"}],"event":{"name":"ICSE-SEIP '26: 2026 IEEE\/ACM 48th International Conference on Software Engineering","location":"Rio de Janeiro Brazil","acronym":"ICSE-SEIP '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"]},"container-title":["Proceedings of the IEEE\/ACM 48th International Conference on Software Engineering: Software Engineering in Practice"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3786583.3786896","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T09:14:12Z","timestamp":1783761252000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786583.3786896"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":44,"alternative-id":["10.1145\/3786583.3786896","10.1145\/3786583"],"URL":"https:\/\/doi.org\/10.1145\/3786583.3786896","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}