{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T02:37:41Z","timestamp":1774579061729,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T00:00:00Z","timestamp":1691107200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Science Foundation of China","award":["No. 62276148"],"award-info":[{"award-number":["No. 62276148"]}]},{"name":"Natural Science Foundation of China","award":["No. 61836013"],"award-info":[{"award-number":["No. 61836013"]}]},{"name":"Natural Science Foundation of China","award":["No. 61825602"],"award-info":[{"award-number":["No. 61825602"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,6]]},"DOI":"10.1145\/3580305.3599790","type":"proceedings-article","created":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T18:13:58Z","timestamp":1691172838000},"page":"5673-5684","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":217,"title":["CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5391-9446","authenticated-orcid":false,"given":"Qinkai","family":"Zheng","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9482-8769","authenticated-orcid":false,"given":"Xiao","family":"Xia","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9471-1481","authenticated-orcid":false,"given":"Xu","family":"Zou","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6092-2002","authenticated-orcid":false,"given":"Yuxiao","family":"Dong","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0887-6861","authenticated-orcid":false,"given":"Shan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7959-0667","authenticated-orcid":false,"given":"Yufei","family":"Xue","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9786-2605","authenticated-orcid":false,"given":"Lei","family":"Shen","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1540-6213","authenticated-orcid":false,"given":"Zihan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2673-9990","authenticated-orcid":false,"given":"Andi","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2485-3951","authenticated-orcid":false,"given":"Yang","family":"Li","sequence":"additional","affiliation":[{"name":"Zhipu.AI, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9517-2845","authenticated-orcid":false,"given":"Teng","family":"Su","sequence":"additional","affiliation":[{"name":"Huawei, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0681-9603","authenticated-orcid":false,"given":"Zhilin","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3487-4593","authenticated-orcid":false,"given":"Jie","family":"Tang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2023,8,4]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Unified pre-training for program understanding and generation. arXiv preprint arXiv:2103.06333","author":"Ahmad Wasi Uddin","year":"2021","unstructured":"Wasi Uddin Ahmad , Saikat Chakraborty , Baishakhi Ray , and Kai-Wei Chang . 2021. Unified pre-training for program understanding and generation. arXiv preprint arXiv:2103.06333 ( 2021 ). Wasi Uddin Ahmad, Saikat Chakraborty, Baishakhi Ray, and Kai-Wei Chang. 2021. Unified pre-training for program understanding and generation. arXiv preprint arXiv:2103.06333 (2021)."},{"key":"e_1_3_2_1_2_1","unstructured":"Jacob Austin Augustus Odena Maxwell Nye Maarten Bosma Henryk Michalewski David Dohan Ellen Jiang Carrie Cai Michael Terry Quoc Le etal 2021. Program synthesis with large language models. arXiv preprint arXiv:2108.07732 (2021).  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_3_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba , Jamie Ryan Kiros, and Geoffrey E Hinton . 2016 . Layer normalization. arXiv preprint arXiv:1607.06450 (2016). Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer normalization. arXiv preprint arXiv:1607.06450 (2016)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Sid Black Stella Biderman Eric Hallahan Quentin Anthony Leo Gao Laurence Golding Horace He Connor Leahy Kyle McDonell Jason Phang etal 2022. Gpt-neox-20b: An open-source autoregressive language model. arXiv preprint arXiv:2204.06745 (2022).  Sid Black Stella Biderman Eric Hallahan Quentin Anthony Leo Gao Laurence Golding Horace He Connor Leahy Kyle McDonell Jason Phang et al. 2022. Gpt-neox-20b: An open-source autoregressive language model. arXiv preprint arXiv:2204.06745 (2022).","DOI":"10.18653\/v1\/2022.bigscience-1.9"},{"key":"e_1_3_2_1_5_1","volume-title":"GPT-Neo: Large Scale Autoregressive Language Modeling with Mesh-Tensorflow. If you use this software, please cite it using these metadata","author":"Black Sid","year":"2021","unstructured":"Sid Black , Leo Gao , Phil Wang , Connor Leahy , and Stella Biderman . 2021. GPT-Neo: Large Scale Autoregressive Language Modeling with Mesh-Tensorflow. If you use this software, please cite it using these metadata , Vol. 58 ( 2021 ). Sid Black, Leo Gao, Phil Wang, Connor Leahy, and Stella Biderman. 2021. GPT-Neo: Large Scale Autoregressive Language Modeling with Mesh-Tensorflow. If you use this software, please cite it using these metadata, Vol. 58 (2021)."},{"key":"e_1_3_2_1_6_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell etal 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877--1901.  Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_7_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). 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_8_1","volume-title":"Charles Sutton, Sebastian Gehrmann, and et al.","author":"Chowdhery Aakanksha","year":"2022","unstructured":"Aakanksha Chowdhery , Sharan Narang , Jacob Devlin , Maarten Bosma , Gaurav Mishra , Adam Roberts , Paul Barham , Hyung Won Chung , Charles Sutton, Sebastian Gehrmann, and et al. 2022 . Palm : Scaling language modeling with pathways. https:\/\/arxiv.org\/abs\/2204.02311 Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, and et al. 2022. Palm: Scaling language modeling with pathways. https:\/\/arxiv.org\/abs\/2204.02311"},{"key":"e_1_3_2_1_9_1","volume-title":"Codebert: A pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155","author":"Feng Zhangyin","year":"2020","unstructured":"Zhangyin Feng , Daya Guo , Duyu Tang , Nan Duan , Xiaocheng Feng , Ming Gong , Linjun Shou , Bing Qin , Ting Liu , Daxin Jiang , 2020 . Codebert: A pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155 (2020). Zhangyin Feng, Daya Guo, Duyu Tang, Nan Duan, Xiaocheng Feng, Ming Gong, Linjun Shou, Bing Qin, Ting Liu, Daxin Jiang, et al. 2020. Codebert: A pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155 (2020)."},{"key":"e_1_3_2_1_10_1","volume-title":"Incoder: A generative model for code infilling and synthesis. arXiv preprint arXiv:2204.05999","author":"Fried Daniel","year":"2022","unstructured":"Daniel Fried , Armen Aghajanyan , Jessy Lin , Sida Wang , Eric Wallace , Freda Shi , Ruiqi Zhong , Wen-tau Yih, Luke Zettlemoyer , and Mike Lewis . 2022 . Incoder: A generative model for code infilling and synthesis. arXiv preprint arXiv:2204.05999 (2022). Daniel Fried, Armen Aghajanyan, Jessy Lin, Sida Wang, Eric Wallace, Freda Shi, Ruiqi Zhong, Wen-tau Yih, Luke Zettlemoyer, and Mike Lewis. 2022. Incoder: A generative model for code infilling and synthesis. arXiv preprint arXiv:2204.05999 (2022)."},{"key":"e_1_3_2_1_11_1","unstructured":"Leo Gao Stella Biderman Sid Black Laurence Golding Travis Hoppe Charles Foster Jason Phang Horace He Anish Thite Noa Nabeshima etal 2020. The pile: An 800gb dataset of diverse text for language modeling. arXiv preprint arXiv:2101.00027 (2020).  Leo Gao Stella Biderman Sid Black Laurence Golding Travis Hoppe Charles Foster Jason Phang Horace He Anish Thite Noa Nabeshima et al. 2020. The pile: An 800gb dataset of diverse text for language modeling. arXiv preprint arXiv:2101.00027 (2020)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_13_1","unstructured":"Dan Hendrycks Steven Basart Saurav Kadavath Mantas Mazeika Akul Arora Ethan Guo Collin Burns Samir Puranik Horace He Dawn Song etal 2021. Measuring coding challenge competence with apps. arXiv preprint arXiv:2105.09938 (2021).  Dan Hendrycks Steven Basart Saurav Kadavath Mantas Mazeika Akul Arora Ethan Guo Collin Burns Samir Puranik Horace He Dawn Song et al. 2021. Measuring coding challenge competence with apps. arXiv preprint arXiv:2105.09938 (2021)."},{"key":"e_1_3_2_1_14_1","volume-title":"Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel . 2016. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 ( 2016 ). Dan Hendrycks and Kevin Gimpel. 2016. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)."},{"key":"e_1_3_2_1_15_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_16_1","volume-title":"Garnett (Eds.)","volume":"32","author":"Kulal Sumith","year":"2019","unstructured":"Sumith Kulal , Panupong Pasupat , Kartik Chandra , Mina Lee , Oded Padon , Alex Aiken , and Percy S Liang . 2019 . SPoC: Search-based Pseudocode to Code. In Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. Alch\u00e9-Buc, E. Fox, and R . Garnett (Eds.) , Vol. 32 . Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/ 2019\/file\/7298332f04ac004a0ca44cc69ecf6f6b-Paper.pdf Sumith Kulal, Panupong Pasupat, Kartik Chandra, Mina Lee, Oded Padon, Alex Aiken, and Percy S Liang. 2019. SPoC: Search-based Pseudocode to Code. In Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/7298332f04ac004a0ca44cc69ecf6f6b-Paper.pdf"},{"key":"e_1_3_2_1_17_1","volume-title":"Agustin Dal Lago, et al","author":"Li Yujia","year":"2022","unstructured":"Yujia Li , David Choi , Junyoung Chung , Nate Kushman , Julian Schrittwieser , R\u00e9mi Leblond , Tom Eccles , James Keeling , Felix Gimeno , Agustin Dal Lago, et al . 2022 . Competition-Level Code Generation with AlphaCode . arXiv preprint arXiv:2203.07814 (2022). Yujia Li, David Choi, Junyoung Chung, Nate Kushman, Julian Schrittwieser, R\u00e9mi Leblond, Tom Eccles, James Keeling, Felix Gimeno, Agustin Dal Lago, et al. 2022. Competition-Level Code Generation with AlphaCode. arXiv preprint arXiv:2203.07814 (2022)."},{"key":"e_1_3_2_1_18_1","volume-title":"Codexglue: A machine learning benchmark dataset for code understanding and generation. arXiv preprint arXiv:2102.04664","author":"Lu Shuai","year":"2021","unstructured":"Shuai Lu , Daya Guo , Shuo Ren , Junjie Huang , Alexey Svyatkovskiy , Ambrosio Blanco , Colin Clement , Dawn Drain , Daxin Jiang , Duyu Tang , 2021 . Codexglue: A machine learning benchmark dataset for code understanding and generation. arXiv preprint arXiv:2102.04664 (2021). Shuai Lu, Daya Guo, Shuo Ren, Junjie Huang, Alexey Svyatkovskiy, Ambrosio Blanco, Colin Clement, Dawn Drain, Daxin Jiang, Duyu Tang, et al. 2021. Codexglue: A machine learning benchmark dataset for code understanding and generation. arXiv preprint arXiv:2102.04664 (2021)."},{"key":"e_1_3_2_1_19_1","volume-title":"On end-to-end program generation from user intention by deep neural networks. arXiv preprint arXiv:1510.07211","author":"Mou Lili","year":"2015","unstructured":"Lili Mou , Rui Men , Ge Li , Lu Zhang , and Zhi Jin . 2015. On end-to-end program generation from user intention by deep neural networks. arXiv preprint arXiv:1510.07211 ( 2015 ). Lili Mou, Rui Men, Ge Li, Lu Zhang, and Zhi Jin. 2015. On end-to-end program generation from user intention by deep neural networks. arXiv preprint arXiv:1510.07211 (2015)."},{"key":"e_1_3_2_1_20_1","volume-title":"A conversational paradigm for program synthesis. arXiv preprint arXiv:2203.13474","author":"Nijkamp Erik","year":"2022","unstructured":"Erik Nijkamp , Bo Pang , Hiroaki Hayashi , Lifu Tu , Huan Wang , Yingbo Zhou , Silvio Savarese , and Caiming Xiong . 2022. A conversational paradigm for program synthesis. arXiv preprint arXiv:2203.13474 ( 2022 ). Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, and Caiming Xiong. 2022. A conversational paradigm for program synthesis. arXiv preprint arXiv:2203.13474 (2022)."},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311--318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni , Salim Roukos , Todd Ward , and Wei-Jing Zhu . 2002 . Bleu: a method for automatic evaluation of machine translation . In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311--318 . Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311--318."},{"key":"e_1_3_2_1_22_1","volume-title":"Cotext: Multi-task learning with code-text transformer. arXiv preprint arXiv:2105.08645","author":"Phan Long","year":"2021","unstructured":"Long Phan , Hieu Tran , Daniel Le , Hieu Nguyen , James Anibal , Alec Peltekian , and Yanfang Ye . 2021 . Cotext: Multi-task learning with code-text transformer. arXiv preprint arXiv:2105.08645 (2021). Long Phan, Hieu Tran, Daniel Le, Hieu Nguyen, James Anibal, Alec Peltekian, and Yanfang Ye. 2021. Cotext: Multi-task learning with code-text transformer. arXiv preprint arXiv:2105.08645 (2021)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2814270.2814310"},{"key":"e_1_3_2_1_24_1","unstructured":"Weizhen Qi Yeyun Gong Yu Yan Can Xu Bolun Yao Bartuer Zhou Biao Cheng Daxin Jiang Jiusheng Chen Ruofei Zhang etal 2021. ProphetNet-x: large-scale pre-training models for English Chinese multi-lingual dialog and code generation. arXiv preprint arXiv:2104.08006 (2021).  Weizhen Qi Yeyun Gong Yu Yan Can Xu Bolun Yao Bartuer Zhou Biao Cheng Daxin Jiang Jiusheng Chen Ruofei Zhang et al. 2021. ProphetNet-x: large-scale pre-training models for English Chinese multi-lingual dialog and code generation. arXiv preprint arXiv:2104.08006 (2021)."},{"key":"e_1_3_2_1_25_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. 2018. Improving language understanding by generative pre training. (2018).  Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. 2018. Improving language understanding by generative pre training. (2018)."},{"key":"e_1_3_2_1_26_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever etal 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9.  Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_2_1_28_1","volume-title":"Codebleu: a method for automatic evaluation of code synthesis. arXiv preprint arXiv:2009.10297","author":"Ren Shuo","year":"2020","unstructured":"Shuo Ren , Daya Guo , Shuai Lu , Long Zhou , Shujie Liu , Duyu Tang , Neel Sundaresan , Ming Zhou , Ambrosio Blanco , and Shuai Ma. 2020. Codebleu: a method for automatic evaluation of code synthesis. arXiv preprint arXiv:2009.10297 ( 2020 ). Shuo Ren, Daya Guo, Shuai Lu, Long Zhou, Shujie Liu, Duyu Tang, Neel Sundaresan, Ming Zhou, Ambrosio Blanco, and Shuai Ma. 2020. Codebleu: a method for automatic evaluation of code synthesis. arXiv preprint arXiv:2009.10297 (2020)."},{"key":"e_1_3_2_1_29_1","volume-title":"Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909","author":"Sennrich Rico","year":"2015","unstructured":"Rico Sennrich , Barry Haddow , and Alexandra Birch . 2015. Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909 ( 2015 ). Rico Sennrich, Barry Haddow, and Alexandra Birch. 2015. Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909 (2015)."},{"key":"e_1_3_2_1_30_1","volume-title":"Program synthesis by sketching","author":"Solar-Lezama Armando","unstructured":"Armando Solar-Lezama . 2008. Program synthesis by sketching . University of California , Berkeley. Armando Solar-Lezama. 2008. Program synthesis by sketching. University of California, Berkeley."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/321992.322002"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6430"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417058"},{"key":"e_1_3_2_1_34_1","volume-title":"Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, Heng-Tze Cheng, Alicia Jin, Taylor Bos, Leslie Baker, Yu Du, et al.","author":"Thoppilan Romal","year":"2022","unstructured":"Romal Thoppilan , Daniel De Freitas , Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, Heng-Tze Cheng, Alicia Jin, Taylor Bos, Leslie Baker, Yu Du, et al. 2022 . Lamda : Language models for dialog applications. arXiv preprint arXiv:2201.08239 (2022). Romal Thoppilan, Daniel De Freitas, Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, Heng-Tze Cheng, Alicia Jin, Taylor Bos, Leslie Baker, Yu Du, et al. 2022. Lamda: Language models for dialog applications. arXiv preprint arXiv:2201.08239 (2022)."},{"key":"e_1_3_2_1_35_1","volume-title":"Natural language processing with transformers. \"O'Reilly Media","author":"Tunstall Lewis","unstructured":"Lewis Tunstall , Leandro von Werra , and Thomas Wolf . 2022. Natural language processing with transformers. \"O'Reilly Media , Inc .\". Lewis Tunstall, Leandro von Werra, and Thomas Wolf. 2022. Natural language processing with transformers. \"O'Reilly Media, Inc.\"."},{"key":"e_1_3_2_1_36_1","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N Gomez , ?ukasz Kaiser, and Illia Polosukhin . 2017. Attention is All you Need . In Advances in Neural Information Processing Systems , I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30 . Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/ 2017 \/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, ?ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the 1st international joint conference on Artificial intelligence. 241--252","author":"Waldinger Richard J","year":"1969","unstructured":"Richard J Waldinger and Richard CT Lee . 1969 . PROW: A step toward automatic program writing . In Proceedings of the 1st international joint conference on Artificial intelligence. 241--252 . Richard J Waldinger and Richard CT Lee. 1969. PROW: A step toward automatic program writing. In Proceedings of the 1st international joint conference on Artificial intelligence. 241--252."},{"key":"e_1_3_2_1_38_1","unstructured":"Ben Wang and Aran Komatsuzaki. 2021. GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model. https:\/\/github.com\/kingoflolz\/mesh-transformer-jax  Ben Wang and Aran Komatsuzaki. 2021. GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model. https:\/\/github.com\/kingoflolz\/mesh-transformer-jax"},{"key":"e_1_3_2_1_39_1","volume-title":"Codet5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. arXiv preprint arXiv:2109.00859","author":"Wang Yue","year":"2021","unstructured":"Yue Wang , Weishi Wang , Shafiq Joty , and Steven CH Hoi . 2021. Codet5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. arXiv preprint arXiv:2109.00859 ( 2021 ). Yue Wang, Weishi Wang, Shafiq Joty, and Steven CH Hoi. 2021. Codet5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. arXiv preprint arXiv:2109.00859 (2021)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Thomas Wolf Lysandre Debut Victor Sanh Julien Chaumond Clement Delangue Anthony Moi Pierric Cistac Tim Rault R\u00e9mi Louf Morgan Funtowicz etal 2019. Huggingface's transformers: State-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019).  Thomas Wolf Lysandre Debut Victor Sanh Julien Chaumond Clement Delangue Anthony Moi Pierric Cistac Tim Rault R\u00e9mi Louf Morgan Funtowicz et al. 2019. Huggingface's transformers: State-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019).","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3520312.3534862"},{"key":"e_1_3_2_1_42_1","unstructured":"Aohan Zeng Xiao Liu Zhengxiao Du Zihan Wang Hanyu Lai Ming Ding Zhuoyi Yang Yifan Xu Wendi Zheng Xiao Xia etal 2022. Glm-130b: An open bilingual pre-trained model. arXiv preprint arXiv:2210.02414 (2022).  Aohan Zeng Xiao Liu Zhengxiao Du Zihan Wang Hanyu Lai Ming Ding Zhuoyi Yang Yifan Xu Wendi Zheng Xiao Xia et al. 2022. Glm-130b: An open bilingual pre-trained model. arXiv preprint arXiv:2210.02414 (2022)."},{"key":"e_1_3_2_1_43_1","unstructured":"Wei Zeng Xiaozhe Ren Teng Su Hui Wang Yi Liao Zhiwei Wang Xin Jiang ZhenZhang Yang Kaisheng Wang Xiaoda Zhang Chen Li Ziyan Gong Yifan Yao Xinjing Huang Jun Wang Jianfeng Yu Qi Guo Yue Yu Yan Zhang Jin Wang Hengtao Tao Dasen Yan Zexuan Yi Fang Peng Fangqing Jiang Han Zhang Lingfeng Deng Yehong Zhang Zhe Lin Chao Zhang Shaojie Zhang Mingyue Guo Shanzhi Gu Gaojun Fan Yaowei Wang Xuefeng Jin Qun Liu and Yonghong Tian. 2021. PanGu-?: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation. (2021).  Wei Zeng Xiaozhe Ren Teng Su Hui Wang Yi Liao Zhiwei Wang Xin Jiang ZhenZhang Yang Kaisheng Wang Xiaoda Zhang Chen Li Ziyan Gong Yifan Yao Xinjing Huang Jun Wang Jianfeng Yu Qi Guo Yue Yu Yan Zhang Jin Wang Hengtao Tao Dasen Yan Zexuan Yi Fang Peng Fangqing Jiang Han Zhang Lingfeng Deng Yehong Zhang Zhe Lin Chao Zhang Shaojie Zhang Mingyue Guo Shanzhi Gu Gaojun Fan Yaowei Wang Xuefeng Jin Qun Liu and Yonghong Tian. 2021. PanGu-?: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation. (2021)."},{"key":"e_1_3_2_1_44_1","volume-title":"Xi Victoria Lin, et al","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, et al . 2022 . Opt : Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022). Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al. 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)."},{"key":"e_1_3_2_1_45_1","volume-title":"XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence. arXiv preprint arXiv:2206.08474","author":"Zhu Ming","year":"2022","unstructured":"Ming Zhu , Aneesh Jain , Karthik Suresh , Roshan Ravindran , Sindhu Tipirneni , and Chandan K Reddy . 2022. XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence. arXiv preprint arXiv:2206.08474 ( 2022 ). Ming Zhu, Aneesh Jain, Karthik Suresh, Roshan Ravindran, Sindhu Tipirneni, and Chandan K Reddy. 2022. XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence. arXiv preprint arXiv:2206.08474 (2022)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3520312.3534864"}],"event":{"name":"KDD '23: The 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Long Beach CA USA","acronym":"KDD '23","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599790","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3580305.3599790","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:23Z","timestamp":1750182563000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599790"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,4]]},"references-count":46,"alternative-id":["10.1145\/3580305.3599790","10.1145\/3580305"],"URL":"https:\/\/doi.org\/10.1145\/3580305.3599790","relation":{},"subject":[],"published":{"date-parts":[[2023,8,4]]},"assertion":[{"value":"2023-08-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}