{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T12:09:01Z","timestamp":1763381341139,"version":"3.45.0"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,17]]},"DOI":"10.1145\/3772356.3772406","type":"proceedings-article","created":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T12:02:48Z","timestamp":1763380968000},"page":"184-192","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Just-in-Time Logic Enforcement"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9707-7291","authenticated-orcid":false,"given":"Hongyu","family":"H\u00e8","sequence":"first","affiliation":[{"name":"Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0342-2631","authenticated-orcid":false,"given":"Maria","family":"Apostolaki","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,11,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Differentiable convex optimization layers. Advances in neural information processing systems 32","author":"Agrawal Akshay","year":"2019","unstructured":"Akshay Agrawal, Brandon Amos, Shane Barratt, Stephen Boyd, Steven Diamond, and J Zico Kolter. 2019. Differentiable convex optimization layers. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_2_1","volume-title":"Non-Invasive Constrained Generation. International Conference on Machine Learning (ICML) abs\/2403","author":"Beurer-Kellner Luca","year":"2024","unstructured":"Luca Beurer-Kellner, Marc Fischer, and Martin T. Vechev. 2024. Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation. International Conference on Machine Learning (ICML) abs\/2403.06988 (2024)."},{"key":"e_1_3_2_1_3_1","volume-title":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 13303\u201313310","author":"Chane-Sane Elliot","year":"2024","unstructured":"Elliot Chane-Sane, Pierre-Alexandre Leziart, Thomas Flayols, Olivier Stasse, Philippe Sou\u00e8res, and Nicolas Mansard. 2024. Cat: Constraints as terminations for legged locomotion reinforcement learning. In 2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 13303\u201313310."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2012.86"},{"key":"e_1_3_2_1_5_1","first-page":"61048","article-title":"On the constrained time-series generation problem","volume":"36","author":"Coletta Andrea","year":"2023","unstructured":"Andrea Coletta, Sriram Gopalakrishnan, Daniel Borrajo, and Svitlana Vyetrenko. 2023. On the constrained time-series generation problem. Advances in Neural Information Processing Systems 36 (2023), 61048\u201361059.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_6_1","unstructured":"Davide Corsi Enrico Marchesini and Alessandro Farinelli. 2021. Formal verification of neural networks for safety-critical tasks in deep reinforcement learning. In Uncertainty in Artificial Intelligence. PMLR 333\u2013343."},{"key":"e_1_3_2_1_7_1","volume-title":"TrafficLLM: Enhancing LLMs for Network Traffic Analysis. arXiv preprint arXiv:2504.04222","author":"Cui Tianyu","year":"2025","unstructured":"Tianyu Cui, Xinjie Lin, Sijia Li, Miao Chen, Qilei Yin, Qi Li, and Ke Xu. 2025. TrafficLLM: Enhancing LLMs for Network Traffic Analysis. arXiv preprint arXiv:2504.04222 (2025). Version 2025-04-05."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-022-01939-z"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the ACM on Networking 2, CoNEXT4","author":"C\u00fcppers Joscha","year":"2024","unstructured":"Joscha C\u00fcppers, Adrien Schoen, Gregory Blanc, and Pierre-Francois Gimenez. 2024. FlowChronicle: Synthetic Network Flow Generation through Pattern Set Mining. Proceedings of the ACM on Networking 2, CoNEXT4 (2024), 1\u201320."},{"key":"e_1_3_2_1_10_1","volume-title":"DC3: A learning method for optimization with hard constraints. arXiv preprint arXiv:2104.12225","author":"Donti Priya L","year":"2021","unstructured":"Priya L Donti, David Rolnick, and J Zico Kolter. 2021. DC3: A learning method for optimization with hard constraints. arXiv preprint arXiv:2104.12225 (2021)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07421-0"},{"key":"e_1_3_2_1_12_1","volume-title":"Grammar-constrained decoding for structured NLP tasks without fine-tuning. arXiv preprint arXiv:2305.13971","author":"Geng Saibo","year":"2023","unstructured":"Saibo Geng, Martin Josifoski, Maxime Peyrard, and Robert West. 2023. Grammar-constrained decoding for structured NLP tasks without fine-tuning. arXiv preprint arXiv:2305.13971 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"Grammar-constrained decoding for structured NLP tasks without fine-tuning. arXiv preprint arXiv:2305.13971","author":"Geng Saibo","year":"2023","unstructured":"Saibo Geng, Martin Josifoski, Maxime Peyrard, and Robert West. 2023. Grammar-constrained decoding for structured NLP tasks without fine-tuning. arXiv preprint arXiv:2305.13971 (2023)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3517745.3561430"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626111.3628188"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672225"},{"key":"e_1_3_2_1_17_1","volume-title":"Improved training of wasserstein gans. Advances in neural information processing systems 30","author":"Gulrajani Ishaan","year":"2017","unstructured":"Ishaan Gulrajani, Faruk Ahmed, Martin Arjovsky, Vincent Dumoulin, and Aaron C Courville. 2017. Improved training of wasserstein gans. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626111.3628176"},{"key":"e_1_3_2_1_19_1","volume-title":"18th USENIX symposium on networked systems design and implementation (NSDI 21)","author":"Hance Travis","year":"2021","unstructured":"Travis Hance, Marijn Heule, Ruben Martins, and Bryan Parno. 2021. Finding invariants of distributed systems: It's a small (enough) world after all. In 18th USENIX symposium on networked systems design and implementation (NSDI 21). 115\u2013131."},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 23rd ACM Workshop on Hot Topics in Networks. 205\u2013212","author":"He Zhiyuan","year":"2024","unstructured":"Zhiyuan He, Aashish Gottipati, Lili Qiu, Xufang Luo, Kenuo Xu, Yuqing Yang, and Francis Y Yan. 2024. Designing Network Algorithms via Large Language Models. In Proceedings of the 23rd ACM Workshop on Hot Topics in Networks. 205\u2013212."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"e_1_3_2_1_22_1","volume-title":"Are LLMs all you need for task-oriented dialogue? arXiv preprint arXiv:2304.06556","author":"Hude\u010dek Vojt\u011bch","year":"2023","unstructured":"Vojt\u011bch Hude\u010dek and Ond\u0159ej Du\u0161ek. 2023. Are LLMs all you need for task-oriented dialogue? arXiv preprint arXiv:2304.06556 (2023)."},{"key":"e_1_3_2_1_23_1","unstructured":"Hongyu H\u00e8 Minhao Jin and Maria Apostolaki. 2025. Making Logic a First-Class Citizen in Network Data Generation with ML. arXiv:2506.23964 [cs.NI] https:\/\/arxiv.org\/abs\/2506.23964"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3639037"},{"key":"e_1_3_2_1_25_1","volume-title":"Robustifying ML-powered Network Classifiers with PANTS. In 34th USENIX Security Symposium (USENIX Security 25)","author":"Jin Minhao","year":"2025","unstructured":"Minhao Jin and Maria Apostolaki. 2025. Robustifying ML-powered Network Classifiers with PANTS. In 34th USENIX Security Symposium (USENIX Security 25)."},{"key":"e_1_3_2_1_26_1","volume-title":"Not only rewards but also constraints: Applications on legged robot locomotion","author":"Kim Yunho","year":"2024","unstructured":"Yunho Kim, Hyunsik Oh, Jeonghyun Lee, Jinhyeok Choi, Gwanghyeon Ji, Moonkyu Jung, Donghoon Youm, and Jemin Hwangbo. 2024. Not only rewards but also constraints: Applications on legged robot locomotion. IEEE Transactions on Robotics (2024)."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"39","author":"Li Haitao","year":"2025","unstructured":"Haitao Li, Qingyao Ai, Jia Chen, Qian Dong, Zhijing Wu, and Yiqun Liu. 2025. Blade: Enhancing black-box large language models with small domain-specific models. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 39. 24422\u201324430."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359651"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626111.3628183"},{"key":"e_1_3_2_1_30_1","volume-title":"arXiv preprint arXiv:2505.06191","author":"Mao Jiayuan","year":"2025","unstructured":"Jiayuan Mao, Joshua B Tenenbaum, and Jiajun Wu. 2025. Neuro-Symbolic Concepts. arXiv preprint arXiv:2505.06191 (2025)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626111.3628194"},{"key":"e_1_3_2_1_32_1","volume-title":"Learning differentiable solvers for systems with hard constraints. arXiv preprint arXiv:2207.08675","author":"N\u00e9giar Geoffrey","year":"2022","unstructured":"Geoffrey N\u00e9giar, Michael W Mahoney, and Aditi S Krishnapriyan. 2022. Learning differentiable solvers for systems with hard constraints. arXiv preprint arXiv:2207.08675 (2022)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696348.3696894"},{"key":"e_1_3_2_1_34_1","volume-title":"Synchromesh: Reliable code generation from pre-trained language models. arXiv preprint arXiv:2201.11227","author":"Poesia Gabriel","year":"2022","unstructured":"Gabriel Poesia, Oleksandr Polozov, Vu Le, Ashish Tiwari, Gustavo Soares, Christopher Meek, and Sumit Gulwani. 2022. Synchromesh: Reliable code generation from pre-trained language models. arXiv preprint arXiv:2201.11227 (2022)."},{"key":"e_1_3_2_1_35_1","volume-title":"Language Models are Unsupervised Multitask Learners. OpenAI Blog 1, 8","author":"Radford Alec","year":"2019","unstructured":"Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. OpenAI Blog 1, 8 (2019). https:\/\/cdn.openai.com\/better-language-models\/language_models_are_unsupervised_multitask_learners.pdf."},{"key":"e_1_3_2_1_36_1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research 21, 140 (2020), 1\u201367.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2018.10.045"},{"key":"e_1_3_2_1_38_1","volume-title":"PI-CARD: Parsing incrementally for constrained auto-regressive decoding from language models. arXiv preprint arXiv:2109.05093","author":"Scholak Torsten","year":"2021","unstructured":"Torsten Scholak, Nathan Schucher, and Dzmitry Bahdanau. 2021. PI-CARD: Parsing incrementally for constrained auto-regressive decoding from language models. arXiv preprint arXiv:2109.05093 (2021)."},{"key":"e_1_3_2_1_39_1","unstructured":"Sungyong Seo Sercan O. Arik Jinsung Yoon Xiang Zhang Kihyuk Sohn and Tomas Pfister. 2021. Controlling Neural Networks with Rule Representations. arXiv:2106.07804 [cs.LG]"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626111.3628205"},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the 18th International Conference on emerging Networking EXperiments and Technologies. 59\u201371","author":"Sharma Rahul Anand","year":"2022","unstructured":"Rahul Anand Sharma, Ishan Sabane, Maria Apostolaki, Anthony Rowe, and Vyas Sekar. 2022. Lumen: a framework for developing and evaluating ML-based IoT network anomaly detection. In Proceedings of the 18th International Conference on emerging Networking EXperiments and Technologies. 59\u201371."},{"key":"e_1_3_2_1_42_1","volume-title":"David Alvarez-Melis, and Nicolo Fusi.","author":"Shen Junhong","year":"2024","unstructured":"Junhong Shen, Neil Tenenholtz, James Brian Hall, David Alvarez-Melis, and Nicolo Fusi. 2024. Tag-LLM: Repurposing general-purpose LLMs for specialized domains. arXiv preprint arXiv:2402.05140 (2024)."},{"key":"e_1_3_2_1_43_1","volume-title":"Solatorio and Olivier Dupriez","author":"Aivin","year":"2023","unstructured":"Aivin V. Solatorio and Olivier Dupriez. 2023. REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers. arXiv preprint arXiv:2302.02041 (2023)."},{"key":"e_1_3_2_1_44_1","volume-title":"Dara Bahri, Zhen Qin, Simon Baumgartner, Cong Yu, and Donald Metzler.","author":"Tay Yi","year":"2021","unstructured":"Yi Tay, Vinh Q Tran, Sebastian Ruder, Jai Gupta, Hyung Won Chung, Dara Bahri, Zhen Qin, Simon Baumgartner, Cong Yu, and Donald Metzler. 2021. Charformer: Fast character transformers via gradient-based subword tokenization. arXiv preprint arXiv:2106.12672 (2021)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934466.2934472"},{"key":"e_1_3_2_1_46_1","volume-title":"Formal Methods and Testing: An Outcome of the FORTEST Network, Revised Selected Papers","author":"Tretmans Jan","unstructured":"Jan Tretmans. 2008. Model based testing with labelled transition systems. In Formal Methods and Testing: An Outcome of the FORTEST Network, Revised Selected Papers. Springer, 1\u201338."},{"key":"e_1_3_2_1_47_1","volume-title":"Philipp Holl, and Nils Thuerey.","author":"Um Kiwon","year":"2020","unstructured":"Kiwon Um, Robert Brand, Yun Raymond Fei, Philipp Holl, and Nils Thuerey. 2020. Solver-in-the-loop: Learning from differentiable physics to interact with iterative pde-solvers. Advances in neural information processing systems 33 (2020), 6111\u20136122."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1007\/BF01160018","article-title":"Logic of transition systems","volume":"3","author":"Benthem Johan Van","year":"1994","unstructured":"Johan Van Benthem and Jan Bergstra. 1994. Logic of transition systems. Journal of Logic, Language and Information 3 (1994), 247\u2013283.","journal-title":"Journal of Logic, Language and Information"},{"key":"e_1_3_2_1_49_1","volume-title":"Incorporating Terminology Constraints in Automatic Post-Editing. In Conference on Machine Translation.","author":"Wan David","year":"2020","unstructured":"David Wan, Chris Kedzie, Faisal Ladhak, Marine Carpuat, and Kathleen McKeown. 2020. Incorporating Terminology Constraints in Automatic Post-Editing. In Conference on Machine Translation."},{"key":"e_1_3_2_1_50_1","volume-title":"Proceedings of the ACM on Networking 2, CoNEXT2, 1\u201325","author":"Wang Changjie","year":"2024","unstructured":"Changjie Wang, Mariano Scazzariello, Alireza Farshin, Simone Ferlin, Dejan Kosti\u0107, and Marco Chiesa. 2024. Netconfeval: Can llms facilitate network configuration? Proceedings of the ACM on Networking 2, CoNEXT2, 1\u201325."},{"key":"e_1_3_2_1_51_1","volume-title":"Efficient guided generation for large language models. arXiv preprint arXiv:2307.09702","author":"Willard Brandon T","year":"2023","unstructured":"Brandon T Willard and R\u00e9mi Louf. 2023. Efficient guided generation for large language models. arXiv preprint arXiv:2307.09702 (2023)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672268"},{"key":"e_1_3_2_1_53_1","volume-title":"Modeling tabular data using conditional gan. Advances in neural information processing systems 32","author":"Xu Lei","year":"2019","unstructured":"Lei Xu, Maria Skoularidou, Alfredo Cuesta-Infante, and Kalyan Veeramachaneni. 2019. Modeling tabular data using conditional gan. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_54_1","volume-title":"Safe neurosymbolic learning with differentiable symbolic execution. arXiv preprint arXiv:2203.07671","author":"Yang Chenxi","year":"2022","unstructured":"Chenxi Yang and Swarat Chaudhuri. 2022. Safe neurosymbolic learning with differentiable symbolic execution. arXiv preprint arXiv:2203.07671 (2022)."},{"key":"e_1_3_2_1_55_1","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Yao Jianan","year":"2022","unstructured":"Jianan Yao, Runzhou Tao, Ronghui Gu, and Jason Nieh. 2022. {DuoAI}: Fast, automated inference of inductive invariants for verifying distributed protocols. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). 485\u2013501."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544251"},{"key":"e_1_3_2_1_57_1","volume-title":"17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20)","author":"Yuan Yifei","year":"2020","unstructured":"Yifei Yuan, Soo-Jin Moon, Sahil Uppal, Limin Jia, and Vyas Sekar. 2020. {NetSMC}: A Custom Symbolic Model Checker for Stateful Network Verification. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20). 181\u2013200."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/2.53"},{"key":"e_1_3_2_1_59_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"38","author":"Zeng Jiali","year":"2024","unstructured":"Jiali Zeng, Fandong Meng, Yongjing Yin, and Jie Zhou. 2024. Teaching large language models to translate with comparison. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38. 19488\u201319496."},{"key":"e_1_3_2_1_60_1","unstructured":"Yedi Zhang Yufan Cai Xinyue Zuo Xiaokun Luan Kailong Wang Zhe Hou Yifan Zhang Zhiyuan Wei Meng Sun Jun Sun et al. 2024. The Fusion of Large Language Models and Formal Methods for Trustworthy AI Agents: A Roadmap. arXiv preprint arXiv:2412.06512 (2024)."},{"key":"e_1_3_2_1_61_1","unstructured":"Yue Zhang Yafu Li Leyang Cui Deng Cai Lemao Liu Tingchen Fu Xinting Huang Enbo Zhao Yu Zhang Yulong Chen et al. 2023. Siren's song in the AI ocean: a survey on hallucination in large language models. arXiv preprint arXiv:2309.01219 (2023)."}],"event":{"name":"HotNets '25: 24th ACM Workshop on Hot Topics in Networks","location":"UMD Campus College Park MD USA","acronym":"HotNets '25","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the 24th ACM Workshop on Hot Topics in Networks"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3772356.3772406","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T12:07:10Z","timestamp":1763381230000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772356.3772406"}},"subtitle":["A new paradigm of combining statistical and symbolic reasoning for network management"],"short-title":[],"issued":{"date-parts":[[2025,11,17]]},"references-count":61,"alternative-id":["10.1145\/3772356.3772406","10.1145\/3772356"],"URL":"https:\/\/doi.org\/10.1145\/3772356.3772406","relation":{},"subject":[],"published":{"date-parts":[[2025,11,17]]},"assertion":[{"value":"2025-11-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}