79 citations · 147 across the 13 of their papers we have counts for
15 papers
TutorCaseBench: A Case-Grounded Benchmark for Evaluating LLM Tutors in Supporting Students with Challenging Behaviors
Yeon Su Park, Chanyoung Park, Tae Soo Kim +5
LLMs are increasingly used as AI tutors, yet existing benchmarks overlook the challenging behaviors common among students with learning and behavioral difficulties. We introduce Tu…
"When to Hand Off, When to Work Together": Understanding Concurrent Human-Agent Interaction in Shared Co-Creative Workspaces
Kihoon Son, Hyewon Lee, DaEun Choi +6
Shared co-creative workspaces allow users to contribute while agents execute. Yet how users adjust their participation as their work and the agent's execution shape one another rem…
DiscoverLLM: From Executing Intents to Discovering Them
Tae Soo Kim, Yoonjoo Lee, Jaesang Yu +2
To handle ambiguous and open-ended requests, Large Language Models (LLMs) are increasingly trained to interact with users to surface intents they have not yet expressed (e.g., ask…
On the Regulatory Potential of User Interfaces for AI Agent Governance
K. J. Kevin Feng, Tae Soo Kim, Rock Yuren Pang +3
AI agents that take actions in their environment autonomously over extended time horizons require robust governance interventions to curb their potentially consequential risks. Pri…
ClearFairy: Capturing Creative Workflows through Decision Structuring, In-Situ Questioning, and Rationale Inference
Kihoon Son, DaEun Choi, Tae Soo Kim +3
Capturing professionals' decision-making in creative workflows (e.g., UI/UX) is essential for reflection, collaboration, and knowledge sharing, yet existing methods often leave rat…
Evalet: Evaluating Large Language Models through Functional Fragmentation
Tae Soo Kim, Heechan Lee, Yoonjoo Lee +2
Practitioners increasingly rely on Large Language Models (LLMs) to evaluate generative AI outputs through "LLM-as-a-Judge" approaches. However, these methods produce holistic score…
CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactions
Tae Soo Kim, Yoonjoo Lee, Yoonah Park +3
Personalization of Large Language Models (LLMs) often assumes users hold static preferences that reflect globally in all tasks. In reality, humans hold dynamic preferences that cha…
One vs. Many: Comprehending Accurate Information from Multiple Erroneous and Inconsistent AI Generations
Yoonjoo Lee, Kihoon Son, Tae Soo Kim +4
As Large Language Models (LLMs) are nondeterministic, the same input can generate different outputs, some of which may be incorrect or hallucinated. If run again, the LLM may corre…
Unveiling Disparities in Web Task Handling Between Human and Web Agent
Kihoon Son, Jinhyeon Kwon, DaEun Choi +4
With the advancement of Large-Language Models (LLMs) and Large Vision-Language Models (LVMs), agents have shown significant capabilities in various tasks, such as data analysis, ga…
Demystifying Tacit Knowledge in Graphic Design: Characteristics, Instances, Approaches, and Guidelines
Kihoon Son, DaEun Choi, Tae Soo Kim +1
Despite the growing demand for professional graphic design knowledge, the tacit nature of design inhibits knowledge sharing. However, there is a limited understanding on the charac…
GenQuery: Supporting Expressive Visual Search with Generative Models
Kihoon Son, DaEun Choi, Tae Soo Kim +2
Designers rely on visual search to explore and develop ideas in early design stages. However, designers can struggle to identify suitable text queries to initiate a search or to di…
EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteria
Tae Soo Kim, Yoonjoo Lee, Jamin Shin +2
By simply composing prompts, developers can prototype novel generative applications with Large Language Models (LLMs). To refine prototypes into products, however, developers must…
Papeos: Augmenting Research Papers with Talk Videos
Tae Soo Kim, Matt Latzke, Jonathan Bragg +2
Research consumption has been traditionally limited to the reading of academic papers-a static, dense, and formally written format. Alternatively, pre-recorded conference presentat…
The Semantic Reader Project: Augmenting Scholarly Documents through AI-Powered Interactive Reading Interfaces
Kyle Lo, Joseph Chee Chang, Andrew Head +52
Scholarly publications are key to the transfer of knowledge from scholars to others. However, research papers are information-dense, and as the volume of the scientific literature…
LMCanvas: Object-Oriented Interaction to Personalize Large Language Model-Powered Writing Environments
Tae Soo Kim, Arghya Sarkar, Yoonjoo Lee +2
Large language models (LLMs) can enhance writing by automating or supporting specific tasks in writers' workflows (e.g., paraphrasing, creating analogies). Leveraging this capabili…