Logo

Tae Soo Kim

I am a fourth year PhD student in the School of Computing at KAIST. I work with Juho Kim as a member of KIXLAB.

My work falls in the intersection of human-computer interaction (HCI) and artificial intelligence (AI), focusing on interactive alignment. Specifically, I explore how to disentangle user inputs and AI outputs into interactive components that empower users to (1) iterate on their intents to guide the AI model, and (2) audit that the model’s behavior aligns with their intents.

Publications

Conference Papers

(Placeholder Title)  Interactive System for Exploring and Evaluating LLM Outputs at Scale
Tae Soo Kim, et al.
Under Review
(Placeholder Title)  Benchmarking Model Ability to Predict Preferences from Interactions
Tae Soo Kim, et al.
Under Review

Posters, Demos, Workshop Papers

Heechan Lee, Tae Soo Kim, Juho Kim
CHI 2025 Workshop on Human-centered Evaluation and Auditing of Language Models (HEAL)
Yoonjoo Lee, Tae Soo Kim, Juho Kim
CHI 2024 Workshop on Human-centered Evaluation and Auditing of Language Models (HEAL)
Kihoon Son, Jinhyeon Kwon, DaEun Choi, Tae Soo Kim, Young-Ho Kim, Sangdoo Yun, Juho Kim
CHI 2024 Workshop on Computational Methodologies for Understanding, Automating, and Evaluating User Interfaces
ACL 2022 Workshop on Intelligent and Interactive Writing Assistants
Saelyne Yang, Sangkyung Kwak, Tae Soo Kim, Juho Kim
CHI 2022 Workshop on Computational Approaches for Understanding, Generating, and Adapting User Interfaces