{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T15:27:41Z","timestamp":1772033261368,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T00:00:00Z","timestamp":1713744000000},"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":[],"published-print":{"date-parts":[[2024,4,22]]},"DOI":"10.1145\/3642970.3655831","type":"proceedings-article","created":{"date-parts":[[2024,4,19]],"date-time":"2024-04-19T10:46:57Z","timestamp":1713523617000},"page":"91-97","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Priority Sampling of Large Language Models for Compilers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3336-0726","authenticated-orcid":false,"given":"Dejan","family":"Grubisic","sequence":"first","affiliation":[{"name":"Rice University, Houston, Texas, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0120-895X","authenticated-orcid":false,"given":"Volker","family":"Seeker","sequence":"additional","affiliation":[{"name":"Meta AI, Menlo Park, California, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1715-3356","authenticated-orcid":false,"given":"Gabriel","family":"Synnaeve","sequence":"additional","affiliation":[{"name":"Meta AI, Menlo Park, California, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0664-4176","authenticated-orcid":false,"given":"Hugh","family":"Leather","sequence":"additional","affiliation":[{"name":"Meta AI, Menlo Park, California, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9026-5453","authenticated-orcid":false,"given":"John","family":"Mellor-Crummey","sequence":"additional","affiliation":[{"name":"Rice University, Houston, Texas, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9382-4302","authenticated-orcid":false,"given":"Chris","family":"Cummins","sequence":"additional","affiliation":[{"name":"Meta AI, Menlo Park, California, USA"}]}],"member":"320","published-online":{"date-parts":[[2024,4,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Fixing hardware security bugs with large language models. arXiv preprint arXiv:2302.01215","author":"Ahmad Baleegh","year":"2023","unstructured":"Baleegh Ahmad, Shailja Thakur, Benjamin Tan, Ramesh Karri, and Hammond Pearce. Fixing hardware security bugs with large language models. arXiv preprint arXiv:2302.01215, 2023."},{"key":"e_1_3_2_1_2_1","volume-title":"Niklas Muennighoff, Mayank Mishra, Alex Gu, Manan Dey, Logesh Kumar Umapathi, Carolyn Jane Anderson, Yangtian Zi, Joel Lamy Poirier, Hailey Schoelkopf, Sergey Troshin, Dmitry Abulkhanov, Manuel Romero","author":"Allal Loubna Ben","year":"2023","unstructured":"Loubna Ben Allal, Raymond Li, Denis Kocetkov, Chenghao Mou, Christopher Akiki, Carlos Munoz Ferrandis, Niklas Muennighoff, Mayank Mishra, Alex Gu, Manan Dey, Logesh Kumar Umapathi, Carolyn Jane Anderson, Yangtian Zi, Joel Lamy Poirier, Hailey Schoelkopf, Sergey Troshin, Dmitry Abulkhanov, Manuel Romero, Michael Lappert, Francesco De Toni, Bernardo Garc\u00eda del R\u00edo, Qian Liu, Shamik Bose, Urvashi Bhattacharyya, Terry Yue Zhuo, Ian Yu, Paulo Villegas, Marco Zocca, Sourab Mangrulkar, David Lansky, Huu Nguyen, Danish Contractor, Luis Villa, Jia Li, Dzmitry Bahdanau, Yacine Jernite, Sean Hughes, Daniel Fried, Arjun Guha, Harm de Vries, and Leandro von Werra. SantaCoder: don't reach for the stars! arXiv:2301.03988, 2023."},{"key":"e_1_3_2_1_3_1","volume-title":"Learning C to x86 Translation: An Experiment in Neural Compilation. arXiv:2108.07639","author":"Armengol-Estap\u00e9 Jordi","year":"2021","unstructured":"Jordi Armengol-Estap\u00e9 and Michael FP O'Boyle. Learning C to x86 Translation: An Experiment in Neural Compilation. arXiv:2108.07639, 2021."},{"key":"e_1_3_2_1_4_1","volume-title":"Nitish Shirish Keskar, and Lav R Varshney. Mirostat: A neural text decoding algorithm that directly controls perplexity. arXiv preprint arXiv:2007.14966","author":"Basu Sourya","year":"2020","unstructured":"Sourya Basu, Govardana Sachitanandam Ramachandran, Nitish Shirish Keskar, and Lav R Varshney. Mirostat: A neural text decoding algorithm that directly controls perplexity. arXiv preprint arXiv:2007.14966, 2020."},{"key":"e_1_3_2_1_5_1","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Ponde de Oliveira Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman Alex Ray Raul Puri Gretchen Krueger Michael Petrov Heidy Khlaaf Girish Sastry Pamela Mishkin Brooke Chan Scott Gray Nick Ryder Mikhail Pavlov Alethea Power Lukasz Kaiser Mohammad Bavarian Clemens Winter Philippe Tillet Felipe Petroski Such Dave Cummings Matthias Plappert Fotios Chantzis Elizabeth Barnes Ariel Herbert-Voss William Hebgen Guss Alex Nichol Alex Paino Nikolas Tezak Jie Tang Igor Babuschkin Suchir Balaji Shantanu Jain William Saunders Christopher Hesse Andrew N. Carr Jan Leike Josh Achiam Vedant Misra Evan Morikawa Alec Radford Matthew Knight Miles Brundage Mira Murati Katie Mayer Peter Welinder Bob McGrew Dario Amodei Sam McCandlish Ilya Sutskever and Wojciech Zaremba. Evaluating Large Language Models Trained on Code. arXiv:2107.03374 2021."},{"key":"e_1_3_2_1_6_1","volume-title":"Noisy parallel approximate decoding for conditional recurrent language model. arXiv preprint arXiv:1605.03835","author":"Cho Kyunghyun","year":"2016","unstructured":"Kyunghyun Cho. Noisy parallel approximate decoding for conditional recurrent language model. arXiv preprint arXiv:1605.03835, 2016."},{"key":"e_1_3_2_1_7_1","volume-title":"Large language models for compiler optimization. arXiv preprint arXiv:2309.07062","author":"Cummins Chris","year":"2023","unstructured":"Chris Cummins, Volker Seeker, Dejan Grubisic, Mostafa Elhoushi, Youwei Liang, Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Kim Hazelwood, Gabriel Synnaeve, et al. Large language models for compiler optimization. arXiv preprint arXiv:2309.07062, 2023."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598067"},{"key":"e_1_3_2_1_9_1","volume-title":"Hierarchical neural story generation. arXiv preprint arXiv:1805.04833","author":"Fan Angela","year":"2018","unstructured":"Angela Fan, Mike Lewis, and Yann Dauphin. Hierarchical neural story generation. arXiv preprint arXiv:1805.04833, 2018."},{"key":"e_1_3_2_1_10_1","first-page":"33","article-title":"Statistical theory of extreme valuse and some practical applications","author":"Gumbel Emil Julius","year":"1954","unstructured":"Emil Julius Gumbel. Statistical theory of extreme valuse and some practical applications. Nat. Bur. Standards Appl. Math. Ser. 33, 1954.","journal-title":"Nat. Bur. Standards Appl. Math. Ser."},{"key":"e_1_3_2_1_11_1","volume-title":"The curious case of neural text degeneration. arXiv preprint arXiv:1904.09751","author":"Holtzman Ari","year":"2019","unstructured":"Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, and Yejin Choi. The curious case of neural text degeneration. arXiv preprint arXiv:1904.09751, 2019."},{"key":"e_1_3_2_1_12_1","first-page":"3499","volume-title":"International Conference on Machine Learning","author":"Kool Wouter","year":"2019","unstructured":"Wouter Kool, Herke Van Hoof, and Max Welling. Stochastic beams and where to find them: The gumbel-top-k trick for sampling sequences without replacement. In International Conference on Machine Learning, pages 3499--3508. PMLR, 2019."},{"key":"e_1_3_2_1_13_1","volume-title":"Unsupervised Translation of Programming Languages. arXiv:2006.03511","author":"Lachaux Marie-Anne","year":"2020","unstructured":"Marie-Anne Lachaux, Baptiste Roziere, Lowik Chanussot, and Guillaume Lample. Unsupervised Translation of Programming Languages. arXiv:2006.03511, 2020."},{"key":"e_1_3_2_1_14_1","volume-title":"Implicit unlikelihood training: Improving neural text generation with reinforcement learning. arXiv preprint arXiv:2101.04229","author":"Lagutin Evgeny","year":"2021","unstructured":"Evgeny Lagutin, Daniil Gavrilov, and Pavel Kalaidin. Implicit unlikelihood training: Improving neural text generation with reinforcement learning. arXiv preprint arXiv:2101.04229, 2021."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403262"},{"key":"e_1_3_2_1_16_1","unstructured":"Raymond Li Loubna Ben Allal Yangtian Zi Niklas Muennighoff Denis Kocetkov Chenghao Mou Marc Marone Christopher Akiki Jia Li Jenny Chim Qian Liu Evgenii Zheltonozhskii Terry Yue Zhuo Thomas Wang Olivier Dehaene Mishig Davaadorj Joel Lamy-Poirier Jo\u00e3o Monteiro Oleh Shliazhko Nicolas Gontier Nicholas Meade Armel Zebaze Ming-Ho Yee Logesh Kumar Umapathi Jian Zhu Benjamin Lipkin Muhtasham Oblokulov Zhiruo Wang Rudra Murthy Jason Stillerman Siva Sankalp Patel Dmitry Abulkhanov Marco Zocca Manan Dey Zhihan Zhang Nour Fahmy Urvashi Bhattacharyya Wenhao Yu Swayam Singh Sasha Luccioni Paulo Villegas Maxim Kunakov Fedor Zhdanov Manuel Romero Tony Lee Nadav Timor Jennifer Ding Claire Schlesinger Hailey Schoelkopf Jan Ebert Tri Dao Mayank Mishra Alex Gu Jennifer Robinson Carolyn Jane Anderson Brendan Dolan-Gavitt Danish Contractor Siva Reddy Daniel Fried Dzmitry Bahdanau Yacine Jernite Carlos Mu\u00f1oz Ferrandis Sean Hughes Thomas Wolf Arjun Guha Leandro von Werra and Harm de Vries. StarCoder: may the source be with you! arXiv:2305.06161 2023."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Yujia Li David Choi Junyoung Chung Nate Kushman Julian Schrittwieser R\u00e9mi Leblond Tom Eccles James Keeling Felix Gimeno Agustin Dal Lago Thomas Hubert Peter Choy Cyprien de Masson d'Autume Igor Babuschkin Xinyun Chen Po-Sen Huang Johannes Welbl Sven Gowal Alexey Cherepanov James Molloy Daniel J. Mankowitz Esme Sutherland Robson Pushmeet Kohli Nando de Freitas Koray Kavukcuoglu and Oriol Vinyals. Competition-level code generation with AlphaCode. Science 378(6624) 2022.","DOI":"10.1126\/science.abq1158"},{"key":"e_1_3_2_1_18_1","volume-title":"Determinantal beam search. arXiv preprint arXiv:2106.07400","author":"Meister Clara","year":"2021","unstructured":"Clara Meister, Martina Forster, and Ryan Cotterell. Determinantal beam search. arXiv preprint arXiv:2106.07400, 2021."},{"key":"e_1_3_2_1_19_1","volume-title":"Typical decoding for natural language generation. arXiv preprint arXiv:2202.00666","author":"Meister Clara","year":"2022","unstructured":"Clara Meister, Tiago Pimentel, Gian Wiher, and Ryan Cotterell. Typical decoding for natural language generation. arXiv preprint arXiv:2202.00666, 2022."},{"key":"e_1_3_2_1_20_1","unstructured":"OpenAI. GPT-4 Technical Report. arXiv:2303.08774 2023."},{"key":"e_1_3_2_1_21_1","volume-title":"Conformal nucleus sampling. arXiv preprint arXiv:2305.02633","author":"Ravfogel Shauli","year":"2023","unstructured":"Shauli Ravfogel, Yoav Goldberg, and Jacob Goldberger. Conformal nucleus sampling. arXiv preprint arXiv:2305.02633, 2023."},{"key":"e_1_3_2_1_22_1","unstructured":"Baptiste Rozi\u00e8re Jonas Gehring Fabian Gloeckle Sten Sootla Itai Gat Xiaoqing Ellen Tan Yossi Adi Jingyu Liu Tal Remez J\u00e9r\u00e9my Rapin Artyom Kozhevnikov Ivan Evtimov Joanna Bitton Manish Bhatt Cristian Canton Ferrer Aaron Grattafiori Wenhan Xiong Alexandre D\u00e9fossez Jade Copet Faisal Azhar Hugo Touvron Louis Martin Nicolas Usunier Thomas Scialom and Gabriel Synnaeve. Code Llama: Open Foundation Models for Code. arXiv:2308.12950 2023."},{"key":"e_1_3_2_1_23_1","volume-title":"Adaptive Test Generation Using a Large Language Model. arXiv:2302.06527","author":"Sch\u00e4fer Max","year":"2023","unstructured":"Max Sch\u00e4fer, Sarah Nadi, Aryaz Eghbali, and Frank Tip. Adaptive Test Generation Using a Large Language Model. arXiv:2302.06527, 2023."},{"key":"e_1_3_2_1_24_1","first-page":"8785","volume-title":"International Conference on Machine Learning","author":"Shi Kensen","year":"2020","unstructured":"Kensen Shi, David Bieber, and Charles Sutton. Incremental sampling without replacement for sequence models. In International Conference on Machine Learning, pages 8785--8795. PMLR, 2020."},{"key":"e_1_3_2_1_25_1","volume-title":"Diverse beam search: Decoding diverse solutions from neural sequence models. arXiv preprint arXiv:1610.02424","author":"Vijayakumar Ashwin K","year":"2016","unstructured":"Ashwin K Vijayakumar, Michael Cogswell, Ramprasath R Selvaraju, Qing Sun, Stefan Lee, David Crandall, and Dhruv Batra. Diverse beam search: Decoding diverse solutions from neural sequence models. arXiv preprint arXiv:1610.02424, 2016."},{"key":"e_1_3_2_1_26_1","first-page":"35120","volume-title":"International Conference on Machine Learning","author":"Vilnis Luke","year":"2023","unstructured":"Luke Vilnis, Yury Zemlyanskiy, Patrick Murray, Alexandre Tachard Passos, and Sumit Sanghai. Arithmetic sampling: parallel diverse decoding for large language models. In International Conference on Machine Learning, pages 35120--35136. PMLR, 2023."},{"key":"e_1_3_2_1_27_1","volume-title":"Neural text generation with unlikelihood training. arXiv preprint arXiv:1908.04319","author":"Welleck Sean","year":"2019","unstructured":"Sean Welleck, Ilia Kulikov, Stephen Roller, Emily Dinan, Kyunghyun Cho, and Jason Weston. Neural text generation with unlikelihood training. arXiv preprint arXiv:1908.04319, 2019."},{"key":"e_1_3_2_1_28_1","volume-title":"Efficient guided generation for large language models. arXiv e-prints","author":"Willard Brandon T","year":"2023","unstructured":"Brandon T Willard and R\u00e9mi Louf. Efficient guided generation for large language models. arXiv e-prints, pages arXiv-2307, 2023."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00129"},{"key":"e_1_3_2_1_30_1","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Xie Yuxi","year":"2023","unstructured":"Yuxi Xie, Kenji Kawaguchi, Yiran Zhao, Xu Zhao, Min-Yen Kan, Junxian He, and Qizhe Xie. Self-evaluation guided beam search for reasoning. In Thirty-seventh Conference on Neural Information Processing Systems, 2023."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3617680"}],"event":{"name":"EuroSys '24: Nineteenth European Conference on Computer Systems","location":"Athens Greece","acronym":"EuroSys '24","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 4th Workshop on Machine Learning and Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3642970.3655831","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3642970.3655831","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:15:50Z","timestamp":1755908150000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3642970.3655831"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,22]]},"references-count":31,"alternative-id":["10.1145\/3642970.3655831","10.1145\/3642970"],"URL":"https:\/\/doi.org\/10.1145\/3642970.3655831","relation":{},"subject":[],"published":{"date-parts":[[2024,4,22]]},"assertion":[{"value":"2024-04-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}