Research output
Work across verification, code intelligence, natural language processing, and formal language theory.
* Equal contribution. Preprints are identified separately from peer-reviewed publications.
Try a different keyword or clear the filters above.
Joonghyuk Hahn, Aditi, Seung-Yeop Baik, Shinwoo Park, Sang-Ki Ko, Yo-Sub Han (2026). EnCur: Curriculum-Based In-Context Learning with Structural Encoding for Code Time Complexity Prediction. Expert Systems With Applications (ESWA) 2026. https://www.sciencedirect.com/science/article/pii/S0957417425027113
Evaluating whether generated code enforces input preconditions, beyond correctness on valid inputs.
Soohan Lim, Joonghyuk Hahn, Hyunwoo Park, Sang-Ki Ko, Yo-Sub Han (2026). ContractEval: A Benchmark for Evaluating Contract-Satisfying Assertions in Code Generation. Findings of ACL 2026. https://aclanthology.org/2026.findings-acl.2112/
Evaluating regex transformations with formal operations and deterministic finite automata equivalence checks.
Joonghyuk Hahn, Yo-Sub Han (2026). Query4Regex: Verifiable Regex Transformation through Formal Operations from NL and DSL Queries. Findings of EACL 2026. https://aclanthology.org/2026.findings-eacl.331/
Localizing vulnerable subpatterns symbolically, then guiding language models to repair regular expressions.
Sicheol Sung, Joonghyuk Hahn, Yo-Sub Han (2026). Repairing Regex Vulnerabilities via Localization-Guided Instructions. EACL 2026. https://aclanthology.org/2026.eacl-long.379/
Hyundong Jin, Joonghyuk Hahn, Yo-Sub Han (2026). A Regex Minimization Benchmark: A PSPACE-Complete Challenge for Language Models. EACL 2026. https://aclanthology.org/2026.eacl-long.375/
Shinwoo Park, Joonghyuk Hahn, Elizabeth Orwig, Sang-Ki Ko, Yo-Sub Han (2025). Advanced Code Time Complexity Prediction Approach Using Contrastive Learning. Engineering Applications of Artificial Intelligence (EAAI) 2025. https://doi.org/10.1016/j.engappai.2025.110631
Joonghyuk Hahn, Hyunjoon Cheon, Yo-Sub Han (2025). Characterizations of M-equivalence and Weak M-relation. International Journal of Foundations of Computer Science (IJFCS) 2025. https://doi.org/10.1142/S0129054125410047
Joonghyuk Hahn, Soohan Lim, Yo-Sub Han (2025). MEC³O: Multi-Expert Consensus for Code Time Complexity Prediction. arXiv. https://arxiv.org/abs/2510.09049
Su-Hyeon Kim, Joonghyuk Hahn, Sooyung Cha, Yo-Sub Han (2025). ECO: Enhanced Code Optimization via Performance-Aware Prompting for Code-LLMs. arXiv. https://arxiv.org/abs/2510.10517
Yejin Lee, Joonghyuk Hahn, Hyeseon Ahn, Yo-Sub Han (2025). AmpleHate: Amplifying the Attention for Versatile Implicit Hate Detection. EMNLP 2025. https://aclanthology.org/2025.emnlp-main.1469/
Seung-Yeop Baik, Joonghyuk Hahn, Jungin Kim, Mingi Jeon, Aditi, Yo-Sub Han, Sang-Ki Ko (2025). CodeComplex: Dataset for Worst-Case Time Complexity Prediction. Findings of EMNLP 2025. https://aclanthology.org/2025.findings-emnlp.1069/
Combining symbolic analysis and semi-supervised learning for code time-complexity prediction.
Joonghyuk Hahn, Hyeseon Ahn, Jungin Kim, Soohan Lim, Yo-Sub Han (2025). TCProF: Time-Complexity Prediction SSL Framework. NAACL 2025. https://aclanthology.org/2025.naacl-long.482/
Hyunjoon Cheon, Joonghyuk Hahn, Yo-Sub Han (2024). On the Decidability of Infix Inclusion Problem. Theory of Computing Systems (ToCS) 2024. https://doi.org/10.1007/s00224-023-10160-w
Ingyu Baek, Joonghyuk Hahn, Yo-Sub Han, Kai Salomaa (2024). Universal Rewriting Rules for the Parikh Matrix Injectivity Problem. DLT 2024, LNCS 14791. https://doi.org/10.1007/978-3-031-66159-4_6
Ju-Hyoung Lee, Joonghyuk Hahn, Hyeon-Tae Seo, Jiho Park, Yo-Sub Han (2024). SuperST: Superficial Self-Training for Few-Shot Text Classification. LREC-COLING 2024. https://aclanthology.org/2024.lrec-main.1341/
J.B. Kim, Hazel Kim, Joonghyuk Hahn, Yo-Sub Han (2023). ATHENA: Mathematical Reasoning with Thought Expansion. EMNLP 2023. https://aclanthology.org/2023.emnlp-main.1014/
Joonghyuk Hahn, Hyunjoon Cheon, Elizabeth Grace Orwig, Su-Hyeon Kim, Sang-Ki Ko, Yo-Sub Han (2023). GDA: Grammar-based Data Augmentation for Text Classification using Slot Information. Findings of EMNLP 2023. https://aclanthology.org/2023.findings-emnlp.486/
Joonghyuk Hahn, Hyunjoon Cheon, Yo-Sub Han (2023). M-equivalence of Parikh Matrix over a Ternary Alphabet. CIAA 2023, LNCS 14151. https://doi.org/10.1007/978-3-031-40247-0_10
Jikyeong Son, Joonghyuk Hahn, Hyeon-Tae Seo, Yo-Sub Han (2022). Boosting Code Summarization by Embedding Code Structures. COLING 2022. https://aclanthology.org/2022.coling-1.521/
Hyunjoon Cheon, Joonghyuk Hahn, Yo-Sub Han (2022). On the Decidability of Infix Inclusion Problem. DLT 2022, LNCS 13257. https://doi.org/10.1007/978-3-031-05578-2_9
Joonghyuk Hahn, Hyunjoon Cheon, Kyuyeol Han, Cheongjae Lee, Junseok Kim, Yo-Sub Han (2021). Self-Training using Rules of Grammar for Few-Shot NLU. Findings of EMNLP 2021. https://aclanthology.org/2021.findings-emnlp.389/
Hyunjoon Cheon, Joonghyuk Hahn, Yo-Sub Han, Sang-Ki Ko (2021). Most Pseudo-copy Languages Are Not Context-free. COCOON 2021. https://doi.org/10.1007/978-3-030-89543-3_16