Donghoon Shin

Jungwoo Lim, Myunghoon Kang, Yuna Hur et al. · nvidia, utoronto

To build a conversational agent that interacts fluently with humans, previous studies blend knowledge or personal profile into the pre-trained language model. However, the model that considers knowledge and persona at the same time is still limited, leading to hallucination and a passive way of using personas. We propose an effective dialogue agent that grounds external knowledge and persona simultaneously. The agent selects the proper knowledge and persona to use for generating the answers with our candidate scoring implemented with a poly-encoder. Then, our model generates the utterance with lesser hallucination and more engagingness utilizing retrieval augmented generation with knowledge-persona enhanced query. We conduct experiments on the persona-knowledge chat and achieve state-of-the-art performance in grounding and generation tasks on the automatic metrics. Moreover, we validate the answers from the models regarding hallucination and engagingness through human evaluation and qualitative results. We show our retriever's effectiveness in extracting relevant documents compared to the other previous retrievers, along with the comparison of multiple candidate scoring methods. Code is available at https://github.com/dlawjddn803/INFO

Donghoon Shin, Gary Hsieh, Young-Ho Kim · uw

Creating personalized and actionable exercise plans often requires iteration with experts, which can be costly and inaccessible to many individuals. This work explores the capabilities of Large Language Models (LLMs) in addressing these challenges. We present PlanFitting, an LLM-driven conversational agent that assists users in creating and refining personalized weekly exercise plans. By engaging users in free-form conversations, PlanFitting helps elicit users' goals, availabilities, and potential obstacles, and enables individuals to generate personalized exercise plans aligned with established exercise guidelines. Our study -- involving a user study, intrinsic evaluation, and expert evaluation -- demonstrated PlanFitting's ability to guide users to create tailored, actionable, and evidence-based plans. We discuss future design opportunities for LLM-driven conversational agents to create plans that better comply with exercise principles and accommodate personal constraints.

Donghoon Shin, Alice Gao, Rock Yuren Pang et al.

Generative AI is known for its tendency to homogenize, often reproducing dominant style conventions found in training data. However, it remains unclear how these homogenizing effects extend to complex structural tasks like web design. As lay creators increasingly turn to LLMs to 'vibe-code' websites -- prompting for aesthetic and functional goals rather than writing code -- they may inadvertently narrow the diversity of their designs, and limit creative expression throughout the internet. In this paper, we interrogate the possibility of design homogenization in web vibe coding. We first characterize the vibe coding lifecycle, pinpointing stages where homogenization risks may arise. We then conduct a sociotechnical risk analysis unpacking the potential harms of web vibe coding and their interaction with design homogenization. We identify that the push for frictionless generation can exacerbate homogenization and its harms. Finally, we propose a mitigation framework centered on the idea of productive friction. Through case studies at the micro, meso, and macro levels, we show how centering productive friction can empower creators to challenge default outputs and preserve diverse expression in AI-mediated web design.

Donghoon Shin, Sejung Lee, Soonmin Bae et al.

We introduce Mi:dm 2.0, a bilingual large language model (LLM) specifically engineered to advance Korea-centric AI. This model goes beyond Korean text processing by integrating the values, reasoning patterns, and commonsense knowledge inherent to Korean society, enabling nuanced understanding of cultural contexts, emotional subtleties, and real-world scenarios to generate reliable and culturally appropriate responses. To address limitations of existing LLMs, often caused by insufficient or low-quality Korean data and lack of cultural alignment, Mi:dm 2.0 emphasizes robust data quality through a comprehensive pipeline that includes proprietary data cleansing, high-quality synthetic data generation, strategic data mixing with curriculum learning, and a custom Korean-optimized tokenizer to improve efficiency and coverage. To realize this vision, we offer two complementary configurations: Mi:dm 2.0 Base (11.5B parameters), built with a depth-up scaling strategy for general-purpose use, and Mi:dm 2.0 Mini (2.3B parameters), optimized for resource-constrained environments and specialized tasks. Mi:dm 2.0 achieves state-of-the-art performance on Korean-specific benchmarks, with top-tier zero-shot results on KMMLU and strong internal evaluation results across language, humanities, and social science tasks. The Mi:dm 2.0 lineup is released under the MIT license to support extensive research and commercial use. By offering accessible and high-performance Korea-centric LLMs, KT aims to accelerate AI adoption across Korean industries, public services, and education, strengthen the Korean AI developer community, and lay the groundwork for the broader vision of K-intelligence. Our models are available at https://huggingface.co/K-intelligence. For technical inquiries, please contact midm-llm@kt.com.

Meziah Ruby Cristobal, Hyeonjeong Byeon, Tze-Yu Chen et al.

The dissemination of scholarly research is critical, yet researchers often lack the time and skills to create engaging content for popular media such as short-form videos. To address this gap, we explore the use of generative AI to help researchers transform their academic papers into accessible video content. Informed by a formative study with science communicators and content creators (N=8), we designed PaperTok, an end-to-end system that automates the initial creative labor by generating script options and corresponding audiovisual content from a source paper. Researchers can then refine based on their preferences with further prompting. A mixed-methods user study (N=18) and crowdsourced evaluation (N=100) demonstrate that PaperTok's workflow can help researchers create engaging and informative short-form videos. We also identified the need for more fine-grained controls in the creation process. To this end, we offer implications for future generative tools that support science outreach.

Donghoon Shin, Lucy Lu Wang, Gary Hsieh · allen-ai, uw

Communicating design implications is common within the HCI community when publishing academic papers, yet these papers are rarely read and used by designers. One solution is to use design cards as a form of translational resource that communicates valuable insights from papers in a more digestible and accessible format to assist in design processes. However, creating design cards can be time-consuming, and authors may lack the resources/know-how to produce cards. Through an iterative design process, we built a system that helps create design cards from academic papers using an LLM and text-to-image model. Our evaluation with designers (N=21) and authors of selected papers (N=12) revealed that designers perceived the design implications from our design cards as more inspiring and generative, compared to reading original paper texts, and the authors viewed our system as an effective way of communicating their design implications. We also propose future enhancements for AI-generated design cards.

Ruican Zhong, Donghoon Shin, Rosemary Meza et al. · uw

This paper explores the integration of causal pathway diagrams (CPD) into human-centered design (HCD), investigating how these diagrams can enhance the early stages of the design process. A dedicated CPD plugin for the online collaborative whiteboard platform Miro was developed to streamline diagram creation and offer real-time AI-driven guidance. Through a user study with designers (N=20), we found that CPD's branching and its emphasis on causal connections supported both divergent and convergent processes during design. CPD can also facilitate communication among stakeholders. Additionally, we found our plugin significantly reduces designers' cognitive workload and increases their creativity during brainstorming, highlighting the implications of AI-assisted tools in supporting creative work and evidence-based designs.

Eungyu Woo, Yooshin Kim, Wonje Heo et al.

Industrial Control Systems (ICS) integrate computing, physical processes, and communication to operate critical infrastructures such as power grids, water treatment plants, and oil and gas facilities. As ICS become increasingly targeted by cyberattacks, timely and reliable anomaly diagnosis is essential for protecting operational safety. However, existing ICS anomaly detection approaches face practical limitations: supervised methods require extensive labeled attack data and suffer from class imbalance, while model-based detectors often lack the ability to provide deep insight into the root causes of anomalies, leading to elevated false alarms and making it difficult for operators to initiate a timely response. In this work, we propose a system-aware unsupervised framework for ICS anomaly diagnosis that combines lightweight online detection with contextual explanation. The system identifies deviations from observed normal behaviors without prior knowledge of system topology. To support actionable response, we further concatenate a contextual digital twin augmented with an Large Language Model (LLM) to enhance interpretability, which translates detection evidence into grounded diagnostic hypotheses and verification steps for operators. Experiments on public ICS benchmarks demonstrate that the proposed framework achieves real-time detection efficiency and provides consistent, interpretable anomaly diagnoses, enabling low-latency warning and practical deployment in complex industrial environments.

Dohoon Kim, Eungyu Woo, Donghoon Shin

This paper investigates a special variant of a pursuit-evasion game called lions and contamination. In a graph where all vertices are initially contaminated, a set of lions traverses the graph, clearing the contamination from every vertex they visit. However, the contamination simultaneously spreads to any adjacent vertex not occupied by a lion. We analyze the relationships among the lion number $\mathcal{L}(G)$, monotone lion number $\mathcal{L}^m(G)$, and the graph's pathwidth $\operatorname{pw}(G)$. Our main results are as follows: (a) We prove a monotonicity property: for any graph $G$ and its isometric subgraph $H$, $\mathcal{L}(H)\le \mathcal{L}(G)$. (b) For trees $T$, we show that the lion number is tightly characterized by pathwidth, satisfying $\operatorname{pw}(T)\le \mathcal{L}(T)\le \operatorname{pw}(T)+1$. (c) We provide a counterexample showing that the monotonicity property fails for arbitrary subgraphs. (d) We show that, in contrast to the tree case, pathwidth does not yield a general lower bound on $\mathcal{L}(G)$ for arbitrary graphs. (e) For any connected graph $G$, we prove the general upper bound $\mathcal{L}(G)\le \operatorname{pw}(G)+1$. (f) For the monotone variant, we establish the general lower bound $\operatorname{pw}(G)\le \mathcal{L}^m(G)$. (g) Conversely, we show that $\mathcal{L}^m(G)\le 2\operatorname{pw}(G)+2$ holds for all connected graphs, which is best possible up to a small additive constant.

Donghoon Shin, Bingcan Guo, Jaewook Lee et al.

Although HCI research papers offer valuable design insights, designers often struggle to apply them in design workflows due to difficulties in finding relevant literature, understanding technical jargon, the lack of contextualization, and limited actionability. To address these challenges, we present ReFinE, a Figma plugin that supports real-time design iteration by surfacing contextualized insights from research papers. ReFinE identifies and synthesizes design implications from HCI literature relevant to the mockup's design context, and tailors this research evidence to a specific design mockup by providing actionable visual guidance on how to update the mockup. To assess the system's effectiveness, we conducted a technical evaluation and a user study. Results show that ReFinE effectively synthesizes and contextualizes design implications, reducing cognitive load and improving designers' ability to integrate research evidence into UI mockups. This work contributes to bridging the gap between research and design practice by presenting a tool for embedding scholarly insights into the UI design process.

Daniel Lee, Nikhil Sharma, Donghoon Shin et al. · uw

Generative AI has made image creation more accessible, yet aligning outputs with nuanced creative intent remains challenging, particularly for non-experts. Existing tools often require users to externalize ideas through prompts or references, limiting fluid exploration. We introduce ThematicPlane, a system that enables users to navigate and manipulate high-level semantic concepts (e.g., mood, style, or narrative tone) within an interactive thematic design plane. This interface bridges the gap between tacit creative intent and system control. In our exploratory study (N=6), participants engaged in divergent and convergent creative modes, often embracing unexpected results as inspiration or iteration cues. While they grounded their exploration in familiar themes, differing expectations of how themes mapped to outputs revealed a need for more explainable controls. Overall, ThematicPlane fosters expressive, iterative workflows and highlights new directions for intuitive, semantics-driven interaction in generative design tools.

Donghoon Shin, Daniel Lee, Gary Hsieh et al. · uw

Poster designing can benefit from synchronous feedback from target audiences. However, gathering audiences with diverse perspectives and reconciling them on design edits can be challenging. Recent generative AI models present opportunities to simulate human-like interactions, but it is unclear how they may be used for feedback processes in design. We introduce PosterMate, a poster design assistant that facilitates collaboration by creating audience-driven persona agents constructed from marketing documents. PosterMate gathers feedback from each persona agent regarding poster components, and stimulates discussion with the help of a moderator to reach a conclusion. These agreed-upon edits can then be directly integrated into the poster design. Through our user study (N=12), we identified the potential of PosterMate to capture overlooked viewpoints, while serving as an effective prototyping tool. Additionally, our controlled online evaluation (N=100) revealed that the feedback from an individual persona agent is appropriate given its persona identity, and the discussion effectively synthesizes the different persona agents' perspectives.

Seojin Hwang, Yumin Kim, Byeongjeong Kim et al.

Large Language Models (LLMs) are integral to applications such as conversational agents and content creation, where precise control over a model's personality is essential for maintaining tone, consistency, and user engagement. However, prevailing prompt-based or fine-tuning approaches either lack robustness or demand large-scale training data, making them costly and impractical. In this paper, we present PALETTE (Personality Adjustment by LLM SElf-TargeTed quEries), a novel method for personality editing in LLMs. Our approach introduces adjustment queries, where self-referential statements grounded in psychological constructs are treated analogously to factual knowledge, enabling direct editing of personality-related responses. Unlike fine-tuning, PALETTE requires only 12 editing samples to achieve substantial improvements in personality alignment across personality dimensions. Experimental results from both automatic and human evaluations demonstrate that our method enables more stable and well-balanced personality control in LLMs.

Donghoon Shin, Subeen Park, Esther Hehsun Kim et al.

Social support in online mental health communities (OMHCs) is an effective and accessible way of managing mental wellbeing. In this process, sharing emotional supports is considered crucial to the thriving social supports in OMHCs, yet often difficult for both seekers and providers. To support empathetic interactions, we design an AI-infused workflow that allows users to write emotional supporting messages to other users' posts based on the elicitation of the seeker's emotion and contextual keywords from writing. Based on a preliminary user study (N = 10), we identified that the system helped seekers to clarify emotion and describe text concretely while writing a post. Providers could also learn how to react empathetically to the post. Based on these results, we suggest design implications for our proposed system.

Yoonna Jang, Jungwoo Lim, Yuna Hur et al.

Humans usually have conversations by making use of prior knowledge about a topic and background information of the people whom they are talking to. However, existing conversational agents and datasets do not consider such comprehensive information, and thus they have a limitation in generating the utterances where the knowledge and persona are fused properly. To address this issue, we introduce a call For Customized conversation (FoCus) dataset where the customized answers are built with the user's persona and Wikipedia knowledge. To evaluate the abilities to make informative and customized utterances of pre-trained language models, we utilize BART and GPT-2 as well as transformer-based models. We assess their generation abilities with automatic scores and conduct human evaluations for qualitative results. We examine whether the model reflects adequate persona and knowledge with our proposed two sub-tasks, persona grounding (PG) and knowledge grounding (KG). Moreover, we show that the utterances of our data are constructed with the proper knowledge and persona through grounding quality assessment.

Donghoon Shin, Sachin Grover, Kenneth Holstein et al.

Explainable AI (XAI) is a promising means of supporting human-AI collaborations for high-stakes visual detection tasks, such as damage detection tasks from satellite imageries, as fully-automated approaches are unlikely to be perfectly safe and reliable. However, most existing XAI techniques are not informed by the understandings of task-specific needs of humans for explanations. Thus, we took a first step toward understanding what forms of XAI humans require in damage detection tasks. We conducted an online crowdsourced study to understand how people explain their own assessments, when evaluating the severity of building damage based on satellite imagery. Through the study with 60 crowdworkers, we surfaced six major strategies that humans utilize to explain their visual damage assessments. We present implications of our findings for the design of XAI methods for such visual detection contexts, and discuss opportunities for future research.

Youjin Hwang, Donghoon Shin, Sion Baek et al.

Conversational agents have been showing lots of opportunities in healthcare by taking over a lot of tasks that used to be done by a human. One of the major functions of conversational healthcare agent is intervening users' daily behaviors. In this case, forming an intimate and trustful relationship with users is one of the major issues. Factors affecting human-agent relationship should be deeply explored to improve long-term acceptance of healthcare agent. Even though a bunch of ideas and researches have been suggested to increase the acceptance of conversational agents in healthcare, challenges still remain. From the preliminary work we conducted, we suggest an idea of applying the personas of users' family members and the doctor who are in the relationship with users in the real world as a solution for forming the rigid relationship between humans and the chatbot.