{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T16:50:50Z","timestamp":1793206250880,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":78,"publisher":"ACM","funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2410856"],"award-info":[{"award-number":["2410856"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2402940"],"award-info":[{"award-number":["2402940"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"DOE U.S. Department of Energy","doi-asserted-by":"publisher","award":["66150"],"award-info":[{"award-number":["66150"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"DOE U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-AC05-76RL01830"],"award-info":[{"award-number":["DE-AC05-76RL01830"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CCI (Commonwealth Cyber Initiative)","award":["HC?3Q24?047"],"award-info":[{"award-number":["HC?3Q24?047"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,20]]},"DOI":"10.1145\/3731545.3731570","type":"proceedings-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T12:46:16Z","timestamp":1757421976000},"page":"1-14","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["FT2: First-Token-Inspired Online Fault Tolerance on Critical Layers for Generative Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7740-6082","authenticated-orcid":false,"given":"Yu","family":"Sun","sequence":"first","affiliation":[{"name":"Department of Computer Science, George Mason University, Fairfax, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0726-1970","authenticated-orcid":false,"given":"Zhu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, George Mason University, Fairfax, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0583-0633","authenticated-orcid":false,"given":"Cherish","family":"Mulpuru","sequence":"additional","affiliation":[{"name":"Department of Computer Science, George Mason University, Fairfax, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9430-2656","authenticated-orcid":false,"given":"Roberto","family":"Gioiosa","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Laboratory, Richland, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5921-0035","authenticated-orcid":false,"given":"Zhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Rutgers University, New Brunswick?Piscataway, New Jersey, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9721-3982","authenticated-orcid":false,"given":"Bo","family":"Fang","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Laboratory, Richland, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0735-8617","authenticated-orcid":false,"given":"Lishan","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, George Mason University, Fairfax, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,9,9]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","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 preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"2023 IEEE 34th International Symposium on Software Reliability Engineering (ISSRE). IEEE, 659\u2013670","author":"Agarwal Udit Kumar","year":"2023","unstructured":"Udit Kumar Agarwal, Abraham Chan, and Karthik Pattabiraman. 2023. Resilience Assessment of Large Language Models under Transient Hardware Faults. In 2023 IEEE 34th International Symposium on Software Reliability Engineering (ISSRE). IEEE, 659\u2013670."},{"key":"e_1_3_2_1_3_1","unstructured":"Fatih Kadir Akin. 2022. Awesome ChatGPT Prompts. https:\/\/huggingface.co\/datasets\/fka\/awesome-chatgpt-prompts."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. 1\u201317","author":"Khoshouyeh Ali Asgari","year":"2023","unstructured":"Ali Asgari Khoshouyeh, Florian Geissler, Syed Qutub, Michael Paulitsch, Prashant Nair, and Karthik Pattabiraman. 2023. Structural coding: A low-cost scheme to protect cnns from large-granularity memory faults. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. 1\u201317."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807670"},{"key":"e_1_3_2_1_6_1","unstructured":"Jacob Austin Augustus Odena Maxwell Nye Maarten Bosma Henryk Michalewski David Dohan Ellen Jiang Carrie Cai Michael Terry Quoc Le et al. 2021. Program Synthesis with Large Language Models. arXiv preprint arXiv:2108.07732 (2021)."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of Findings of EMNLP.","author":"Barbieri Francesco","year":"2020","unstructured":"Francesco Barbieri, Jose Camacho-Collados, Luis Espinosa-Anke, and Leonardo Neves. 2020. TweetEval:Unified Benchmark and Comparative Evaluation for Tweet Classification. In Proceedings of Findings of EMNLP."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/MDT.2005.69"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2021.3105697"},{"key":"e_1_3_2_1_10_1","volume-title":"2019 IEEE International Symposium on High Performance Computer Architecture (HPCA). IEEE, 147\u2013158","author":"Chandramoorthy Nandhini","year":"2019","unstructured":"Nandhini Chandramoorthy, Karthik Swaminathan, Martin Cochet, Arun Paidimarri, Schuyler Eldridge, Rajiv V Joshi, Matthew M Ziegler, Alper Buyuktosunoglu, and Pradip Bose. 2019. Resilient low voltage accelerators for high energy efficiency. In 2019 IEEE International Symposium on High Performance Computer Architecture (HPCA). IEEE, 147\u2013158."},{"key":"e_1_3_2_1_11_1","volume-title":"Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al.","author":"Chen Mark","year":"2021","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 preprint arXiv:2107.03374 (2021)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN48987.2021.00018"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE5003.2020.00047"},{"key":"e_1_3_2_1_14_1","volume-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See https:\/\/vicuna.lmsys.org (accessed","author":"Chiang Wei-Lin","year":"2023","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. See https:\/\/vicuna.lmsys.org (accessed 14 April 2023) 2, 3 (2023), 6."},{"key":"e_1_3_2_1_15_1","volume-title":"Training Verifiers to Solve Math Word Problems. arXiv preprint arXiv:2110.14168","author":"Cobbe Karl","year":"2021","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 preprint arXiv:2110.14168 (2021)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_17_1","volume-title":"2019 IEEE International Symposium on High Performance Computer Architecture (HPCA). IEEE, 238\u2013249","author":"dos Santos Fernando Fernandes","year":"2019","unstructured":"Fernando Fernandes dos Santos, Caio Lunardi, Daniel Oliveira, Fabiano Libano, and Paolo Rech. 2019. Reliability evaluation of mixed-precision architectures. In 2019 IEEE International Symposium on High Performance Computer Architecture (HPCA). IEEE, 238\u2013249."},{"key":"e_1_3_2_1_18_1","volume-title":"2024 IEEE International Conference on Cluster Computing (CLUSTER). IEEE, 166\u2013178","author":"Fang Bo","year":"2024","unstructured":"Bo Fang, Xinyi Li, Harvey Dam, Cheng Tan, Siva Kumar Sastry Hari, Timothy Tsai, Ignacio Laguna, Dingwen Tao, Ganesh Gopalakrishnan, Prashant Nair, et al. 2024. Understanding Mixed Precision GEMM with MPGemmFI: Insights into Fault Resilience. In 2024 IEEE International Conference on Cluster Computing (CLUSTER). IEEE, 166\u2013178."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER59578.2024.00022"},{"key":"e_1_3_2_1_20_1","volume-title":"Performance Analysis of Systems and Software (ISPASS), 2014 IEEE International Symposium on. IEEE, 221\u2013230","author":"Fang Bo","year":"2014","unstructured":"Bo Fang, Karthik Pattabiraman, Matei Ripeanu, and Sudhanva Gurumurthi. 2014. GPU-Qin: A methodology for evaluating the error resilience of GPGPU applications. In Performance Analysis of Systems and Software (ISPASS), 2014 IEEE International Symposium on. IEEE, 221\u2013230."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Vinicius Fratin Daniel A. G. de Oliveira Caio B. Lunardi Fernando Santos Gennaro Rodrigues and Paolo Rech. 2018. Code-Dependent and Architecture-Dependent Reliability Behaviors. In DSN. 13\u201326.","DOI":"10.1109\/DSN.2018.00015"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. 1\u201314","author":"Georgakoudis Giorgis","year":"2017","unstructured":"Giorgis Georgakoudis, Ignacio Laguna, Dimitrios S Nikolopoulos, and Martin Schulz. 2017. Refine: Realistic fault injection via compiler-based instrumentation for accuracy, portability and speed. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. 1\u201314."},{"key":"e_1_3_2_1_23_1","volume-title":"In-place zero-space memory protection for cnn. Advances in Neural Information Processing Systems 32","author":"Guan Hui","year":"2019","unstructured":"Hui Guan, Lin Ning, Zhen Lin, Xipeng Shen, Huiyang Zhou, and Seung-Hwan Lim. 2019. In-place zero-space memory protection for cnn. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580688"},{"key":"e_1_3_2_1_25_1","volume-title":"Error detecting and error correcting codes. The Bell system technical journal 29, 2","author":"Hamming Richard W","year":"1950","unstructured":"Richard W Hamming. 1950. Error detecting and error correcting codes. The Bell system technical journal 29, 2 (1950), 147\u2013160."},{"key":"e_1_3_2_1_26_1","volume-title":"28th USENIX Security Symposium (USENIX Security 19)","author":"Hong Sanghyun","year":"2019","unstructured":"Sanghyun Hong, Pietro Frigo, Yi\u011fitcan Kaya, Cristiano Giuffrida, and Tudor Dumitras,. 2019. Terminal brain damage: Exposing the graceless degradation in deep neural networks under hardware fault attacks. In 28th USENIX Security Symposium (USENIX Security 19). 497\u2013514."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1147\/rd.144.0395"},{"key":"e_1_3_2_1_28_1","volume-title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization. CoRR abs\/2003.11080","author":"Hu Junjie","year":"2020","unstructured":"Junjie Hu, Sebastian Ruder, Aditya Siddhant, Graham Neubig, Orhan Firat, and Melvin Johnson. 2020. XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization. CoRR abs\/2003.11080 (2020). arXiv:2003.11080"},{"key":"e_1_3_2_1_29_1","volume-title":"Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al.","author":"Jiang Albert Q","year":"2024","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al. 2024. Mixtral of experts. arXiv preprint arXiv:2401.04088 (2024)."},{"key":"e_1_3_2_1_30_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)."},{"key":"e_1_3_2_1_31_1","volume-title":"2024 IEEE International Symposium on Workload Characterization (IISWC). IEEE, 57\u201367","author":"Kundu Joyjit","year":"2024","unstructured":"Joyjit Kundu, Wenzhe Guo, Ali BanaGozar, Udari De Alwis, Sourav Sengupta, Puneet Gupta, and Arindam Mallik. 2024. Performance modeling and workload analysis of distributed large language model training and inference. In 2024 IEEE International Symposium on Workload Characterization (IISWC). IEEE, 57\u201367."},{"key":"e_1_3_2_1_32_1","volume-title":"Discrete-event simulation: A first course","author":"Leemis Lawrence M","unstructured":"Lawrence M Leemis and Stephen Keith Park. 2006. Discrete-event simulation: A first course. Pearson Prentice Hall Upper Saddle River, NJ. pg. 366."},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the Conference on Design, Automation and Test in Europe. European Design and Automation Association, 502\u2013506","author":"Leveugle R\u00e9gis","year":"2009","unstructured":"R\u00e9gis Leveugle, A Calvez, Paolo Maistri, and Pierre Vanhauwaert. 2009. Statistical fault injection: Quantified error and confidence. In Proceedings of the Conference on Design, Automation and Test in Europe. European Design and Automation Association, 502\u2013506."},{"key":"e_1_3_2_1_34_1","volume-title":"2019 IEEE international symposium on performance analysis of systems and software (ISPASS). IEEE, 151\u2013152","author":"Lew Jonathan","year":"2019","unstructured":"Jonathan Lew, Deval A Shah, Suchita Pati, Shaylin Cattell, Mengchi Zhang, Amruth Sandhupatla, Christopher Ng, Negar Goli, Matthew D Sinclair, Timothy G Rogers, et al. 2019. Analyzing machine learning workloads using a detailed GPU simulator. In 2019 IEEE international symposium on performance analysis of systems and software (ISPASS). IEEE, 151\u2013152."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126964"},{"key":"e_1_3_2_1_36_1","volume-title":"2018 48th Annual IEEE\/IFIP International Conference on Dependable Systems and Networks (DSN). IEEE, 279\u2013290","author":"Li Guanpeng","year":"2018","unstructured":"Guanpeng Li and Karthik Pattabiraman. 2018. Modeling input-dependent error propagation in programs. In 2018 48th Annual IEEE\/IFIP International Conference on Dependable Systems and Networks (DSN). IEEE, 279\u2013290."},{"key":"e_1_3_2_1_37_1","volume-title":"Light-Weight Fault Tolerant Attention for Large Language Model Training. arXiv preprint arXiv:2410.11720","author":"Liang Yuhang","year":"2024","unstructured":"Yuhang Liang, Xinyi Li, Jie Ren, Ang Li, Bo Fang, and Jieyang Chen. 2024. Light-Weight Fault Tolerant Attention for Large Language Model Training. arXiv preprint arXiv:2410.11720 (2024)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3710848.3710870"},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings, Part V 13","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part V 13. Springer, 740\u2013755."},{"key":"e_1_3_2_1_40_1","volume-title":"ALBERTA: ALgorithm-Based Error Resilience in Transformer Architectures","author":"Liu Haoxuan","year":"2024","unstructured":"Haoxuan Liu, Vasu Singh, Micha\u0142 Filipiuk, and Siva Kumar Sastry Hari. 2024. ALBERTA: ALgorithm-Based Error Resilience in Transformer Architectures. IEEE Open Journal of the Computer Society (2024)."},{"key":"e_1_3_2_1_41_1","volume-title":"On llms-driven synthetic data generation, curation, and evaluation: A survey. arXiv preprint arXiv:2406.15126","author":"Long Lin","year":"2024","unstructured":"Lin Long, Rui Wang, Ruixuan Xiao, Junbo Zhao, Xiao Ding, Gang Chen, and Haobo Wang. 2024. On llms-driven synthetic data generation, curation, and evaluation: A survey. arXiv preprint arXiv:2406.15126 (2024)."},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","volume":"3","author":"Ma Dongning","year":"2024","unstructured":"Dongning Ma, Fred Lin, Alban Desmaison, Joel Coburn, Daniel Moore, Sriram Sankar, and Xun Jiao. 2024. Dr. DNA: Combating Silent Data Corruptions in Deep Learning using Distribution of Neuron Activations. In Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3. 239\u2013252."},{"key":"e_1_3_2_1_43_1","volume-title":"2023 IEEE European Test Symposium (ETS). IEEE, 1\u20136.","author":"Ma Kwondo","year":"2023","unstructured":"Kwondo Ma, Chandramouli Amarnath, and Abhijit Chatterjee. 2023. Error Resilient Transformers: A Novel Soft Error Vulnerability Guided Approach to Error Checking and Suppression. In 2023 IEEE European Test Symposium (ETS). IEEE, 1\u20136."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN-W50199.2020.00014"},{"key":"e_1_3_2_1_45_1","volume-title":"PyTorchFI: A Runtime Perturbation Tool for DNNs. In 2020 50th Annual IEEE\/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W). 25\u201331","author":"Mahmoud A.","year":"2020","unstructured":"A. Mahmoud, N. Aggarwal, A. Nobbe, J. R. S. Vicarte, S. V. Adve, C. W. Fletcher, I. Frosio, and S. K. S. Hari. 2020. PyTorchFI: A Runtime Perturbation Tool for DNNs. In 2020 50th Annual IEEE\/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W). 25\u201331."},{"key":"e_1_3_2_1_46_1","volume-title":"2020 50th Annual IEEE\/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W). IEEE, 25\u201331","author":"Mahmoud Abdulrahman","year":"2020","unstructured":"Abdulrahman Mahmoud, Neeraj Aggarwal, Alex Nobbe, Jose Rodrigo Sanchez Vicarte, Sarita V Adve, Christopher W Fletcher, Iuri Frosio, and Siva Kumar Sastry Hari. 2020. Pytorchfi: A runtime perturbation tool for dnns. In 2020 50th Annual IEEE\/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W). IEEE, 25\u201331."},{"key":"e_1_3_2_1_47_1","volume-title":"2017 IEEE Aerospace Conference. IEEE, 1\u20137.","author":"Milluzzi Andrew","year":"2017","unstructured":"Andrew Milluzzi and Alan George. 2017. Exploration of TMR fault masking with persistent threads on Tegra GPU SoCs. In 2017 IEEE Aerospace Conference. IEEE, 1\u20137."},{"key":"e_1_3_2_1_48_1","volume-title":"Large language models: A survey. arXiv preprint arXiv:2402.06196","author":"Minaee Shervin","year":"2024","unstructured":"Shervin Minaee, Tomas Mikolov, Narjes Nikzad, Meysam Chenaghlu, Richard Socher, Xavier Amatriain, and Jianfeng Gao. 2024. Large language models: A survey. arXiv preprint arXiv:2402.06196 (2024)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S18-1001"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3175930"},{"key":"e_1_3_2_1_51_1","volume-title":"High Performance Computer Architecture (HPCA), 2016 IEEE International Symposium on. IEEE, 519\u2013530","author":"Nie Bin","year":"2016","unstructured":"Bin Nie, Devesh Tiwari, Saurabh Gupta, Evgenia Smirni, and James H Rogers. 2016. A large-scale study of soft-errors on GPUs in the field. In High Performance Computer Architecture (HPCA), 2016 IEEE International Symposium on. IEEE, 519\u2013530."},{"key":"e_1_3_2_1_52_1","volume-title":"MASCOTS","author":"Nie Bin","year":"2017","unstructured":"Bin Nie, Ji Xue, Saurabh Gupta, Christian Engelmann, Evgenia Smirni, and Devesh Tiwari. 2017. Characterizing Temperature, Power, and Soft-Error Behaviors in Data Center Systems: Insights, Challenges, and Opportunities. In MASCOTS 2017. 22\u201331."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650200.3656615"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2124"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00130"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3195997"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3655688"},{"key":"e_1_3_2_1_58_1","volume-title":"Aspis: Lightweight Neural Network Protection Against Soft Errors. In 2024 IEEE 35th International Symposium on Software Reliability Engineering (ISSRE). IEEE, 248\u2013259","author":"Schmedding Anna","year":"2024","unstructured":"Anna Schmedding, Lishan Yang, Adwait Jog, and Evgenia Smirni. 2024. Aspis: Lightweight Neural Network Protection Against Soft Errors. In 2024 IEEE 35th International Symposium on Software Reliability Engineering (ISSRE). IEEE, 248\u2013259."},{"key":"e_1_3_2_1_59_1","volume-title":"SAFECOMP 2018, V\u00e4ster\u00e5s, Sweden, September 19\u201321, 2018, Proceedings 37","author":"Schorn Christoph","year":"2018","unstructured":"Christoph Schorn, Andre Guntoro, and Gerd Ascheid. 2018. Efficient on-line error detection and mitigation for deep neural network accelerators. In Computer Safety, Reliability, and Security: 37th International Conference, SAFECOMP 2018, V\u00e4ster\u00e5s, Sweden, September 19\u201321, 2018, Proceedings 37. Springer, 205\u2013219."},{"key":"e_1_3_2_1_60_1","volume-title":"Global Clipper: Enhancing Safety and Reliability of Transformer-based Object Detection Models. arXiv preprint arXiv:2406.03229","author":"Sha Qutub Syed","year":"2024","unstructured":"Qutub Syed Sha, Michael Paulitsch, Karthik Pattabiraman, Korbinian Hagn, Fabian Oboril, Cornelius Buerkle, Kay-Ulrich Scholl, Gereon Hinz, and Alois Knoll. 2024. Global Clipper: Enhancing Safety and Reliability of Transformer-based Object Detection Models. arXiv preprint arXiv:2406.03229 (2024)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1109\/TDMR.2005.856487","article-title":"Cache and memory error detection, correction, and reduction techniques for terrestrial servers and workstations","volume":"5","author":"Slayman Charles W","year":"2005","unstructured":"Charles W Slayman. 2005. Cache and memory error detection, correction, and reduction techniques for terrestrial servers and workstations. IEEE Transactions on Device and Materials Reliability 5, 3 (2005), 397\u2013404.","journal-title":"IEEE Transactions on Device and Materials Reliability"},{"key":"e_1_3_2_1_62_1","unstructured":"Shaden Smith Mostofa Patwary Brandon Norick Patrick LeGresley Samyam Rajbhandari Jared Casper Zhun Liu Shrimai Prabhumoye George Zerveas Vijay Korthikanti et al. 2022. Using deepspeed and megatron to train megatron-turing nlg 530b a large-scale generative language model. arXiv preprint arXiv:2201.11990 (2022)."},{"key":"e_1_3_2_1_63_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth Katie Millican et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_64_1","volume-title":"Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12)","author":"Tiedemann J\u00f6rg","year":"2012","unstructured":"J\u00f6rg Tiedemann. 2012. Parallel Data, Tools and Interfaces in OPUS. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Mehmet U\u011fur Do\u011fan, Bente Maegaard, Joseph Mariani, Asuncion Moreno, Jan Odijk, and Stelios Piperidis (Eds.). European Language Resources Association (ELRA), Istanbul, Turkey, 2214\u20132218. http:\/\/www.lrec-conf.org\/proceedings\/lrec2012\/pdf\/463_Paper.pdf"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807666"},{"key":"e_1_3_2_1_66_1","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar Aurelien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. arXiv:2302.13971 [cs.CL]"},{"key":"e_1_3_2_1_67_1","unstructured":"Ben Wang and Aran Komatsuzaki. 2021. GPT-J-6B: A 6 billion parameter autoregressive language model."},{"key":"e_1_3_2_1_68_1","volume-title":"2014 44th Annual IEEE\/IFIP International Conference on Dependable Systems and Networks. IEEE, 375\u2013382","author":"Wei Jiesheng","year":"2014","unstructured":"Jiesheng Wei, Anna Thomas, Guanpeng Li, and Karthik Pattabiraman. 2014. Quantifying the accuracy of high-level fault injection techniques for hardware faults. In 2014 44th Annual IEEE\/IFIP International Conference on Dependable Systems and Networks. IEEE, 375\u2013382."},{"key":"e_1_3_2_1_69_1","volume-title":"DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data. arXiv preprint arXiv:2405.14333","author":"Xin Huajian","year":"2024","unstructured":"Huajian Xin, Daya Guo, Zhihong Shao, Zhizhou Ren, Qihao Zhu, Bo Liu, Chong Ruan, Wenda Li, and Xiaodan Liang. 2024. DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data. arXiv preprint arXiv:2405.14333 (2024)."},{"key":"e_1_3_2_1_70_1","unstructured":"An Yang Baosong Yang Binyuan Hui Bo Zheng Bowen Yu Chang Zhou Chengpeng Li Chengyuan Li Dayiheng Liu Fei Huang Guanting Dong Haoran Wei Huan Lin Jialong Tang Jialin Wang Jian Yang Jianhong Tu Jianwei Zhang Jianxin Ma Jianxin Yang Jin Xu Jingren Zhou Jinze Bai Jinzheng He Junyang Lin Kai Dang Keming Lu Keqin Chen Kexin Yang Mei Li Mingfeng Xue Na Ni Pei Zhang Peng Wang Ru Peng Rui Men Ruize Gao Runji Lin Shijie Wang Shuai Bai Sinan Tan Tianhang Zhu Tianhao Li Tianyu Liu Wenbin Ge Xiaodong Deng Xiaohuan Zhou Xingzhang Ren Xinyu Zhang Xipin Wei Xuancheng Ren Xuejing Liu Yang Fan Yang Yao Yichang Zhang Yu Wan Yunfei Chu Yuqiong Liu Zeyu Cui Zhenru Zhang Zhifang Guo and Zhihao Fan. 2024. Qwen2 Technical Report. arXiv:2407.10671 [cs.CL] https:\/\/arxiv.org\/abs\/2407.10671"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00114"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2980541"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2980541"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3447375","article-title":"SUGAR: Speeding Up GPGPU Application Resilience Estimation with Input Sizing","volume":"5","author":"Yang Lishan","year":"2021","unstructured":"Lishan Yang, Bin Nie, Adwait Jog, and Evgenia Smirni. 2021. SUGAR: Speeding Up GPGPU Application Resilience Estimation with Input Sizing. Proceedings of the ACM on Measurement and Analysis of Computing Systems 5, 1 (2021), 1\u201329.","journal-title":"Proceedings of the ACM on Measurement and Analysis of Computing Systems"},{"key":"e_1_3_2_1_75_1","volume-title":"GPU Reliability Assessment: Insights Across the Abstraction Layers. In 2024 IEEE International Conference on Cluster Computing (CLUSTER). IEEE, 1\u201313","author":"Yang Lishan","year":"2024","unstructured":"Lishan Yang, George Papadimitriou, Dimitris Sartzetakis, Adwait Jog, Evgenia Smirni, and Dimitris Gizopoulos. 2024. GPU Reliability Assessment: Insights Across the Abstraction Layers. In 2024 IEEE International Conference on Cluster Computing (CLUSTER). IEEE, 1\u201313."},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"crossref","first-page":"3414","DOI":"10.1109\/TCAD.2021.3129114","article-title":"Improving fault tolerance for reliable DNN using boundary-aware activation","volume":"41","author":"Zhan Jinyu","year":"2021","unstructured":"Jinyu Zhan, Ruoxu Sun, Wei Jiang, Yucheng Jiang, Xunzhao Yin, and Cheng Zhuo. 2021. Improving fault tolerance for reliable DNN using boundary-aware activation. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 41, 10 (2021), 3414\u20133425.","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.148"},{"key":"e_1_3_2_1_78_1","volume-title":"Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer.","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer. 2022. OPT: Open Pre-trained Transformer Language Models. arXiv:2205.01068 [cs.CL] https:\/\/arxiv.org\/abs\/2205.01068"}],"event":{"name":"HPDC '25: 34th International Symposium on High-Performance Parallel and Distributed Computing","location":"University of Notre Dame Conference Facilities Notre Dame IN USA","acronym":"HPDC '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 34th International Symposium on High-Performance Parallel and Distributed Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731545.3731570","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T12:49:22Z","timestamp":1757422162000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731545.3731570"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,20]]},"references-count":78,"alternative-id":["10.1145\/3731545.3731570","10.1145\/3731545"],"URL":"https:\/\/doi.org\/10.1145\/3731545.3731570","relation":{},"subject":[],"published":{"date-parts":[[2025,7,20]]},"assertion":[{"value":"2025-09-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}