Suyoung Bae

I am a Ph.D. student at Sungkyunkwan University, South Korea. I am a member of Information & Intelligence System Laboratory (IISLAB) advised by Prof. Jee-Hyong Lee.

I am researching about Trustwirthy AI, Robust and Efficient Learning, Agentic AI, and Code & Data Intelligence. Specifically, I am interested in the following categories.

[A] Trustworthy AI :Bias & Hallucination Mitigation, AI Ethics/Morality, Evaluation
[B] Robust and Efficient Learning : Robust Learning, Reinforcement Learning, RAG, Recommendation System
[C] Agentic AI : Long Horizon Agent, Multi-Agent System, Memory Management, Self-evolving
[D] Code & Data Intelligence : Repository-Level Code Documentation / Generation / Localization, Evaluation, Text-to-SQL, Table Understanding

Email / CV / LinkedIn / Scholar / Github

News

[September. 2026] 1 papers accepted to NeurIPS 2026.
[Auguest. 2026] 2 papers accepted to EMNLP 2026.
[July. 2026] 3 papers presented at ACL 2026.
[Auguest. 2026 ~ Oct. 2026]: Start Visiting Scholar at Oslo University (Norway).
[March. 2026]: 1 paper accepted to ICLR 2026 Workshop.
[Auguest. 2025]: I received a Ph.D fellowship from National Research Foundation (NRF) of Korea.
[April. 2025] 2 papers presented at NAACL 2025.

International Publications

	[C][D] Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation Suyoung Bae, Jaehoon Lee, Changkyu Choi, YunSeok Choi, Jee-Hyong Lee The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS 2026) [Arxiv]
	[B][C][D] A^2Agent: Action-Aware Reinforcement Learning for RepositoryLevel Code Localization Agents Doyeon Kim, Suyoung Bae, Yumin Lee, Jee-Hyong Lee (* : equal contribution) The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP-Main), 2026 Budapest, Hungary, Obtober 24-29, 2026 [Paper] [Code]
	[C] InterventionBench: Can LLM Agents Adapt to Mid-task User Interventions? Jaehoon Lee, Suyoung Bae, Jin-Seop Lee, YunSeok Choi, Jee-Hyong Lee The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP-Findings), 2026 Budapest, Hungary, Obtober 24-29, 2026 [Paper] [Code]
	[A][D] ReFEree: Reference-Free and Fine-Grained Method for Evaluating Factual Consistency in Real-World Code Summarization Suyoung Bae, CheolWon Na, Jaehoon Lee, Yumin Lee, YunSeok Choi, JeeHyong Lee The 64th Annual Meeting of the Association for Computational Linguistics (ACL-Main), 2026 San Diego, California, United States, July 2–7, 2026 [Paper] [Code]
	[D] EXPO-SQL: Execution-based Clause-level Policy Optimization for Text-toSQL Jaehoon Lee, CheolWon Na, Suyoung Bae, Jin-Seop Lee, Jihyung Lee, YunSeok Choi, Jee-Hyong Lee The 64th Annual Meeting of the Association for Computational Linguistics (ACL-Findings), 2026 San Diego, California, United States, July 2–7, 2026 [Paper]
	[B] UCGRec: User-Centric Graph Learning for LLM-based Sequential Recommendation CheolWon Na, HanBeul Kim, Suyoung Bae, YunSeok Choi, Jee-Hyong Lee The 64th Annual Meeting of the Association for Computational Linguistics (ACL-Findings), 2026 San Diego, California, United States, July 2–7, 2026 [Paper]
	[C] Adversarial Robustness in LLM-Based Multi-Agent Trading Systems: A Systematic Vulnerability Analysis CheolWon Na, Suyoung Bae, Jaehoon Lee, Jee-Hyong Lee The 2nd ICLR Workship on Advances in Financial AI: Towards Agentic and Responsible Systems (ICLR Workshop), 2026 Rio de Janeiro, Brazil, April 27, 2026 [Paper]
	[A] DeCAP: Context-Adaptive Prompt Generation for Debiasing Zero-shot Question Answering in Large Language Models Suyoung Bae, YunSeok Choi, Jee-Hyong Lee Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL-main), 2025 Albuquerque, New Mexico April 29 - May 4, 2025 [Paper] [Code] [Presentation]
	[B] SALAD: Improving Robustness and Generalization through Contrastive Learning with Structure-Aware and LLM-Driven Augmented Data Suyoung Bae, Hyojun Kim, YunSeok Choi, Jee-Hyong Lee (* : equal contribution) Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL-main), 2025 Albuquerque, New Mexico April 29 - May 4, 2025 [Paper] [Presentation]
	[A] CharMoral: A Character Morality Dataset for Morally Dynamic Character Analysis in Long-Form Narratives Suyoung Bae, Gunhee Cho , Boyang Li, Yun-Gyung Cheong Proceedings of the 31st International Conference on Computational Linguistics (COLING-main), 2025 Abu Dhabi, UAE, January 19 - 24, 2025 [Paper] [Code] [Presentation]
	[A] Predicting the Morality of a Character Using Character-Centric Embeddings Suyoung Bae, Eunchong Kim, Yun-Gyung Cheong IEEE International Conference on Big Data and Smart Computing (BigComp), 2023 Jeju, South Korea, 13-16 February, 2023 [Paper]
	The CreativeSumm 2022 Shared Task: A Two-Stage Summarization Model using Scene Attributes Eunchong Kim, Taewoo Yoo, Gunhee Cho, Suyoung Bae, Yun-Gyung Cheong (* : equal contribution) Proceedings of The Workshop on Automatic Summarization for Creative Writing (COLING Workshop), 2022 Gyeongju, South Korea, 12-17 October, 2022 [Paper]