E-mail: [email protected]

Github

Linkedin

Google Scholar

About

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 fairness, truthfulness, and robustness in Natural Language Processing. Specifically, I am interested in the following categories.

• Bias/Hallucination in Large Language Models
• Ethics and Fairness
• Robustness and Generalization in Language Models
• Question Answering Models
• Long-form Summarization Models

Papers

DeCAP: Context-Adaptive Prompt Generation for Debiasing Zero-shot Question Answering in Large Language Models (To be appear)

• Suyoung Bae, YunSeok Choi, Jee-Hyong Lee
• 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL main)
• Albuquerque, New Mexico April 29 – May 4, 2025
• [Paper]

SALAD: Improving Robustness and Generalization through Contrastive Learning with Structure-Aware and LLM-Driven Augmented Data (To be appear)

• Suyoung Bae*, Hyojun Kim*, YunSeok Choi, Jee-Hyong Lee (* : equal contribution)
• 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL main)
• Albuquerque, New Mexico April 29 – May 4, 2025
• [Paper]

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)
• Abu Dhabi, UAE, January 19 – 24, 2025
• [Paper] [Code]

Predicting the Morality of a Character Using Character-Centric Embeddings

• Suyoung Bae, Eun Chong Kim, Yun Gyung Cheong
• 2023 IEEE International Conference on Big Data and Smart Computing (BigComp)
• 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)
• Gyeongju, South Korea, 12-17 October, 2022
• [Paper]

Improving Document Retrieval Model Multi-Domain Dialogue Dataset

• Suyoung Bae, Eun-Chong Kim, Yun-Gyung Cheong
• 2022년 한국컴퓨터종합학술대회 (KCC)
• Jeju, South Korea, June 29 - July 01, 2022
• [Paper]

Educations

<aside> <img src="/icons/graduate_gray.svg" alt="/icons/graduate_gray.svg" width="40px" /> Ph.D., Artificial Intelligence, Sungkyunkwan University (Mar. 2024 - present)

</aside>

<aside> <img src="/icons/graduate_gray.svg" alt="/icons/graduate_gray.svg" width="40px" /> M.S., Artificial Intelligence, Sungkyunkwan University (Mar. 2022 - Feb. 2024)

(GPA: 4.13/4.5)

</aside>