{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T05:57:52Z","timestamp":1780466272258,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671609","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:55:12Z","timestamp":1724561712000},"page":"5430-5441","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["MFTCoder: Boosting Code LLMs with Multitask Fine-Tuning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9380-6168","authenticated-orcid":false,"given":"Bingchang","family":"Liu","sequence":"first","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6133-4324","authenticated-orcid":false,"given":"Chaoyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7142-8433","authenticated-orcid":false,"given":"Zi","family":"Gong","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6393-9035","authenticated-orcid":false,"given":"Cong","family":"Liao","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3333-7195","authenticated-orcid":false,"given":"Huan","family":"Wang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1599-4675","authenticated-orcid":false,"given":"Zhichao","family":"Lei","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3622-1510","authenticated-orcid":false,"given":"Ming","family":"Liang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9532-7636","authenticated-orcid":false,"given":"Dajun","family":"Chen","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8418-1877","authenticated-orcid":false,"given":"Min","family":"Shen","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0476-4449","authenticated-orcid":false,"given":"Hailian","family":"Zhou","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6605-9793","authenticated-orcid":false,"given":"Wei","family":"Jiang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5639-0912","authenticated-orcid":false,"given":"Hang","family":"Yu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8645-0680","authenticated-orcid":false,"given":"Jianguo","family":"Li","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Muppet: Massive Multi-task Representations with Pre-Finetuning. arxiv: 2101.11038 [cs.CL]","author":"Aghajanyan Armen","year":"2021","unstructured":"Armen Aghajanyan, Anchit Gupta, Akshat Shrivastava, Xilun Chen, Luke Zettlemoyer, and Sonal Gupta. 2021. Muppet: Massive Multi-task Representations with Pre-Finetuning. arxiv: 2101.11038 [cs.CL]"},{"key":"e_1_3_2_2_2_1","unstructured":"Loubna Ben Allal Raymond Li Denis Kocetkov et al. 2023. SantaCoder: don't reach for the stars!arxiv: 2301.03988 [cs.SE]"},{"key":"e_1_3_2_2_3_1","unstructured":"Rohan Anil Andrew M. Dai Orhan Firat et al. 2023. PaLM 2 Technical Report. arxiv: 2305.10403 [cs.CL]"},{"key":"e_1_3_2_2_4_1","unstructured":"Anthropic. 2023. Model Card and Evaluations for Claude Models. https:\/\/www-files.anthropic.com\/production\/images\/Model-Card-Claude-2.pdf"},{"key":"e_1_3_2_2_5_1","volume-title":"Sanket Vaibhav Mehta, Honglei Zhuang, Vinh Q. Tran, Dara Bahri, Jianmo Ni, Jai Gupta, Kai Hui, Sebastian Ruder, and Donald Metzler.","author":"Aribandi Vamsi","year":"2022","unstructured":"Vamsi Aribandi, Yi Tay, Tal Schuster, Jinfeng Rao, Huaixiu Steven Zheng, Sanket Vaibhav Mehta, Honglei Zhuang, Vinh Q. Tran, Dara Bahri, Jianmo Ni, Jai Gupta, Kai Hui, Sebastian Ruder, and Donald Metzler. 2022. ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning. arxiv: 2111.10952 [cs.CL]"},{"key":"e_1_3_2_2_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_2_7_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu et al. 2023. Qwen Technical Report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_2_8_1","volume-title":"Baichuan 2: Open Large-scale Language Models. arXiv preprint arXiv:2309.10305","year":"2023","unstructured":"Baichuan. 2023. Baichuan 2: Open Large-scale Language Models. arXiv preprint arXiv:2309.10305 (2023). https:\/\/arxiv.org\/abs\/2309.10305"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"crossref","unstructured":"Sid Black Stella Biderman Eric Hallahan et al. 2022. GPT-NeoX-20B: An Open-Source Autoregressive Language Model. arxiv: 2204.06745 [cs.CL]","DOI":"10.18653\/v1\/2022.bigscience-1.9"},{"key":"e_1_3_2_2_10_1","volume-title":"Multitask learning. Machine learning","author":"Caruana Rich","year":"1997","unstructured":"Rich Caruana. 1997. Multitask learning. Machine learning, Vol. 28 (1997), 41--75."},{"key":"e_1_3_2_2_11_1","volume-title":"Molly Q Feldman, Arjun Guha, Michael Greenberg, and Abhinav Jangda.","author":"Cassano Federico","year":"2022","unstructured":"Federico Cassano, John Gouwar, Daniel Nguyen, Sydney Nguyen, Luna Phipps-Costin, Donald Pinckney, Ming-Ho Yee, Yangtian Zi, Carolyn Jane Anderson, Molly Q Feldman, Arjun Guha, Michael Greenberg, and Abhinav Jangda. 2022. MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation. arxiv: 2208.08227 [cs.LG]"},{"key":"e_1_3_2_2_12_1","unstructured":"Mark Chen Jerry Tworek Heewoo Jun et al. 2021. Evaluating Large Language Models Trained on Code. (2021). arxiv: 2107.03374 [cs.LG]"},{"key":"e_1_3_2_2_13_1","volume-title":"International conference on machine learning. PMLR, 794--803","author":"Chen Zhao","year":"2018","unstructured":"Zhao Chen, Vijay Badrinarayanan, Chen-Yu Lee, and Andrew Rabinovich. 2018. Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks. In International conference on machine learning. PMLR, 794--803."},{"key":"e_1_3_2_2_14_1","unstructured":"Zixiang Chen Yihe Deng Yue Wu Quanquan Gu and Yuanzhi Li. 2022. Towards Understanding Mixture of Experts in Deep Learning. arxiv: 2208.02813 [cs.LG]"},{"key":"e_1_3_2_2_15_1","unstructured":"Aakanksha Chowdhery Sharan Narang Jacob Devlin et al. 2022. PaLM: Scaling Language Modeling with Pathways. arxiv: 2204.02311 [cs.CL]"},{"key":"e_1_3_2_2_16_1","unstructured":"Fenia Christopoulou Gerasimos Lampouras Milan Gritta et al. 2022. PanGu-Coder: Program Synthesis with Function-Level Language Modeling. arxiv: 2207.11280 [cs.LG]"},{"key":"e_1_3_2_2_17_1","volume-title":"Multi-task learning with deep neural networks: A survey. arXiv preprint arXiv:2009.09796","author":"Crawshaw Michael","year":"2020","unstructured":"Michael Crawshaw. 2020. Multi-task learning with deep neural networks: A survey. arXiv preprint arXiv:2009.09796 (2020)."},{"key":"e_1_3_2_2_18_1","unstructured":"Tim Dettmers Artidoro Pagnoni Ari Holtzman and Luke Zettlemoyer. 2023. QLoRA: Efficient Finetuning of Quantized LLMs. arxiv: 2305.14314 [cs.LG]"},{"key":"e_1_3_2_2_19_1","unstructured":"Peng Di Jianguo Li Hang Yu et al. 2023. CodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model. arxiv: 2310.06266 [cs.SE]"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2139"},{"key":"e_1_3_2_2_22_1","volume-title":"Allie Del Giorno, Sivakanth Gopi, Mojan Javaheripi, Piero Kauffmann, Gustavo de Rosa, Olli Saarikivi, et al.","author":"Gunasekar Suriya","year":"2023","unstructured":"Suriya Gunasekar, Yi Zhang, Jyoti Aneja, Caio C\u00e9sar Teodoro Mendes, Allie Del Giorno, Sivakanth Gopi, Mojan Javaheripi, Piero Kauffmann, Gustavo de Rosa, Olli Saarikivi, et al. 2023. Textbooks Are All You Need. arXiv preprint arXiv:2306.11644 (2023)."},{"key":"e_1_3_2_2_23_1","unstructured":"Daya Guo Qihao Zhu Dejian Yang Zhenda Xie Kai Dong Wentao Zhang Guanting Chen Xiao Bi Y. Wu Y. K. Li Fuli Luo Yingfei Xiong and Wenfeng Liang. 2024. DeepSeek-Coder: When the Large Language Model Meets Programming - The Rise of Code Intelligence. arxiv: 2401.14196 [cs.SE]"},{"key":"e_1_3_2_2_24_1","volume-title":"Parameter-Efficient Transfer Learning for NLP. arxiv","author":"Houlsby Neil","year":"1902","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin de Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-Efficient Transfer Learning for NLP. arxiv: 1902.00751 [cs.LG]"},{"key":"e_1_3_2_2_25_1","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 [cs.CL]"},{"key":"e_1_3_2_2_26_1","volume-title":"Adaptive scheduling for multi-task learning. arXiv preprint arXiv:1909.06434","author":"Jean S\u00e9bastien","year":"2019","unstructured":"S\u00e9bastien Jean, Orhan Firat, and Melvin Johnson. 2019. Adaptive scheduling for multi-task learning. arXiv preprint arXiv:1909.06434 (2019)."},{"key":"e_1_3_2_2_27_1","unstructured":"Albert Q. Jiang Alexandre Sablayrolles Arthur Mensch et al. 2023. Mistral 7B. arxiv: 2310.06825 [cs.CL]"},{"key":"e_1_3_2_2_28_1","unstructured":"Albert Q. Jiang Alexandre Sablayrolles Antoine Roux et al. 2024. Mixtral of Experts. arxiv: 2401.04088 [cs.LG]"},{"key":"e_1_3_2_2_29_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 7482--7491","author":"Kendall Alex","year":"2018","unstructured":"Alex Kendall, Yarin Gal, and Roberto Cipolla. 2018. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In Proceedings of the IEEE conference on computer vision and pattern recognition. 7482--7491."},{"key":"e_1_3_2_2_30_1","volume-title":"Daniel Fried, Sida Wang, and Tao Yu.","author":"Lai Yuhang","year":"2022","unstructured":"Yuhang Lai, Chengxi Li, Yiming Wang, Tianyi Zhang, Ruiqi Zhong, Luke Zettlemoyer, Scott Wen tau Yih, Daniel Fried, Sida Wang, and Tao Yu. 2022. DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation. ArXiv, Vol. abs\/2211.11501 (2022)."},{"key":"e_1_3_2_2_31_1","volume-title":"International Conference on Machine Learning. PMLR, 2956--2964","author":"Lee Hae Beom","year":"2018","unstructured":"Hae Beom Lee, Eunho Yang, and Sung Ju Hwang. 2018. Deep asymmetric multi-task feature learning. In International Conference on Machine Learning. PMLR, 2956--2964."},{"key":"e_1_3_2_2_32_1","volume-title":"Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem.","author":"Li Guohao","year":"2023","unstructured":"Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023. CAMEL: Communicative Agents for \"Mind\" Exploration of Large Scale Language Model Society. arxiv: 2303.17760 [cs.AI]"},{"key":"e_1_3_2_2_33_1","unstructured":"Jinyang Li Binyuan Hui Ge Qu Binhua Li Jiaxi Yang Bowen Li Bailin Wang Bowen Qin Rongyu Cao Ruiying Geng Nan Huo Xuanhe Zhou Chenhao Ma Guoliang Li Kevin C. C. Chang Fei Huang Reynold Cheng and Yongbin Li. 2023 d. Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs. arxiv: 2305.03111 [cs.CL]"},{"key":"e_1_3_2_2_34_1","volume-title":"Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, et al.","author":"Li Raymond","year":"2023","unstructured":"Raymond Li, Loubna Ben Allal, Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, et al. 2023. StarCoder: may the source be with you! arXiv preprint arXiv:2305.06161 (2023)."},{"key":"e_1_3_2_2_35_1","volume-title":"Suriya Gunasekar, and Yin Tat Lee.","author":"Li Yuanzhi","year":"2023","unstructured":"Yuanzhi Li, S\u00e9bastien Bubeck, Ronen Eldan, Allie Del Giorno, Suriya Gunasekar, and Yin Tat Lee. 2023. Textbooks Are All You Need II: textbfphi-1.5 technical report. arXiv preprint arXiv:2309.05463 (2023)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.abq1158"},{"key":"e_1_3_2_2_37_1","unstructured":"Tsung-Yi Lin Priya Goyal Ross Girshick Kaiming He and Piotr Doll\u00e1r. 2018. Focal Loss for Dense Object Detection. arxiv: 1708.02002 [cs.CV]"},{"key":"e_1_3_2_2_38_1","volume-title":"FAMO: Fast Adaptive Multitask Optimization. arxiv: 2306.03792 [cs.LG]","author":"Liu Bo","year":"2023","unstructured":"Bo Liu, Yihao Feng, Peter Stone, and Qiang Liu. 2023. FAMO: Fast Adaptive Multitask Optimization. arxiv: 2306.03792 [cs.LG]"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019977"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1441"},{"key":"e_1_3_2_2_42_1","volume-title":"Learning multiple tasks with multilinear relationship networks. Advances in neural information processing systems","author":"Long Mingsheng","year":"2017","unstructured":"Mingsheng Long, Zhangjie Cao, Jianmin Wang, and Philip S Yu. 2017. Learning multiple tasks with multilinear relationship networks. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_43_1","volume-title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct. arXiv preprint arXiv:2306.08568","author":"Luo Ziyang","year":"2023","unstructured":"Ziyang Luo, Can Xu, Pu Zhao, Qingfeng Sun, Xiubo Geng, Wenxiang Hu, Chongyang Tao, Jing Ma, Qingwei Lin, and Daxin Jiang. 2023. WizardCoder: Empowering Code Large Language Models with Evol-Instruct. arXiv preprint arXiv:2306.08568 (2023)."},{"key":"e_1_3_2_2_44_1","volume-title":"A Pilot Study for Chinese SQL Semantic Parsing. arxiv","author":"Min Qingkai","year":"1909","unstructured":"Qingkai Min, Yuefeng Shi, and Yue Zhang. 2019. A Pilot Study for Chinese SQL Semantic Parsing. arxiv: 1909.13293 [cs.CL]"},{"key":"e_1_3_2_2_45_1","volume-title":"Swayam Singh, Xiangru Tang, Leandro von Werra, and Shayne Longpre.","author":"Muennighoff Niklas","year":"2023","unstructured":"Niklas Muennighoff, Qian Liu, Armel Zebaze, Qinkai Zheng, Binyuan Hui, Terry Yue Zhuo, Swayam Singh, Xiangru Tang, Leandro von Werra, and Shayne Longpre. 2023. OctoPack: Instruction Tuning Code Large Language Models. arxiv: 2308.07124 [cs.CL]"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17125"},{"key":"e_1_3_2_2_48_1","unstructured":"Phind. 2023. Phind-CodeLlama-34B-v2. https:\/\/huggingface.co\/Phind\/Phind-CodeLlama-34B-v2"},{"key":"e_1_3_2_2_49_1","unstructured":"Colin Raffel Noam Shazeer Adam Roberts et al. 2023. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. arxiv: 1910.10683 [cs.LG]"},{"key":"e_1_3_2_2_50_1","volume-title":"Yossi Adi, Jingyu Liu, Tal Remez, J\u00e9r\u00e9my Rapin, et al.","author":"Rozi\u00e8re Baptiste","year":"2023","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, et al. 2023. Code llama: Open foundation models for code. arXiv preprint arXiv:2308.12950 (2023)."},{"key":"e_1_3_2_2_51_1","unstructured":"Bo Shen Jiaxin Zhang Taihong Chen Daoguang Zan Bing Geng An Fu Muhan Zeng Ailun Yu Jichuan Ji Jingyang Zhao et al. 2023. Pangu-coder2: Boosting large language models for code with ranking feedback. arXiv preprint arXiv:2307.14936 (2023)."},{"key":"e_1_3_2_2_52_1","first-page":"8728","article-title":"Adashare: Learning what to share for efficient deep multi-task learning","volume":"33","author":"Sun Ximeng","year":"2020","unstructured":"Ximeng Sun, Rameswar Panda, Rogerio Feris, and Kate Saenko. 2020. Adashare: Learning what to share for efficient deep multi-task learning. Advances in Neural Information Processing Systems, Vol. 33 (2020), 8728--8740.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_53_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)."},{"key":"e_1_3_2_2_54_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","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 preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_2_55_1","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 preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_2_56_1","volume-title":"Self-instruct: Aligning language model with self generated instructions. arXiv preprint arXiv:2212.10560","author":"Wang Yizhong","year":"2022","unstructured":"Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A Smith, Daniel Khashabi, and Hannaneh Hajishirzi. 2022. Self-instruct: Aligning language model with self generated instructions. arXiv preprint arXiv:2212.10560 (2022)."},{"key":"e_1_3_2_2_57_1","volume-title":"Nghi D. Q. Bui, Junnan Li, and Steven C. H. Hoi.","author":"Wang Yue","year":"2023","unstructured":"Yue Wang, Hung Le, Akhilesh Deepak Gotmare, Nghi D. Q. Bui, Junnan Li, and Steven C. H. Hoi. 2023. CodeT5: Open Code Large Language Models for Code Understanding and Generation. arxiv: 2305.07922 [cs.CL]"},{"key":"e_1_3_2_2_58_1","volume-title":"Trace Norm Regularised Deep Multi-Task Learning. In 5th International Conference on Learning Representations.","author":"Yang Yongxin","year":"2017","unstructured":"Yongxin Yang and Timothy Hospedales. 2017. Trace Norm Regularised Deep Multi-Task Learning. In 5th International Conference on Learning Representations."},{"key":"e_1_3_2_2_59_1","volume-title":"He Yang Er, et al","author":"Yu Tao","year":"2019","unstructured":"Tao Yu, Rui Zhang, He Yang Er, et al. 2019. CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases. arxiv: 1909.05378 [cs.CL]"},{"key":"e_1_3_2_2_60_1","volume-title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task. arxiv","author":"Yu Tao","year":"2019","unstructured":"Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, Zilin Zhang, and Dragomir Radev. 2019. Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task. arxiv: 1809.08887 [cs.CL]"},{"key":"e_1_3_2_2_61_1","unstructured":"Ziyin Zhang Chaoyu Chen Bingchang Liu Cong Liao Zi Gong Hang Yu Jianguo Li and Rui Wang. 2024. Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code. arxiv: 2311.07989 [cs.CL]"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_25"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"crossref","unstructured":"Qinkai Zheng Xiao Xia Xu Zou Yuxiao Dong Shan Wang Yufei Xue Zihan Wang Lei Shen Andi Wang Yang Li Teng Su Zhilin Yang and Jie Tang. 2023. CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Evaluations on HumanEval-X. In KDD.","DOI":"10.1145\/3580305.3599790"},{"key":"e_1_3_2_2_64_1","volume-title":"Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning. CoRR","author":"Zhong Victor","year":"2017","unstructured":"Victor Zhong, Caiming Xiong, and Richard Socher. 2017. Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning. CoRR, Vol. abs\/1709.00103 (2017)."}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain","acronym":"KDD '24","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 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671609","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:05:59Z","timestamp":1750291559000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671609"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":63,"alternative-id":["10.1145\/3637528.3671609","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671609","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}