SoHyun Park

Yunyong Ko, Seongeun Ryu, Soeun Han et al.

The political stance prediction for news articles has been widely studied to mitigate the echo chamber effect -- people fall into their thoughts and reinforce their pre-existing beliefs. The previous works for the political stance problem focus on (1) identifying political factors that could reflect the political stance of a news article and (2) capturing those factors effectively. Despite their empirical successes, they are not sufficiently justified in terms of how effective their identified factors are in the political stance prediction. Motivated by this, in this work, we conduct a user study to investigate important factors in political stance prediction, and observe that the context and tone of a news article (implicit) and external knowledge for real-world entities appearing in the article (explicit) are important in determining its political stance. Based on this observation, we propose a novel knowledge-aware approach to political stance prediction (KHAN), employing (1) hierarchical attention networks (HAN) to learn the relationships among words and sentences in three different levels and (2) knowledge encoding (KE) to incorporate external knowledge for real-world entities into the process of political stance prediction. Also, to take into account the subtle and important difference between opposite political stances, we build two independent political knowledge graphs (KG) (i.e., KG-lib and KG-con) by ourselves and learn to fuse the different political knowledge. Through extensive evaluations on three real-world datasets, we demonstrate the superiority of DASH in terms of (1) accuracy, (2) efficiency, and (3) effectiveness.

Inhwa Song, SoHyun Park, Sachin R. Pendse et al.

Expressing stressful experiences in words is proven to improve mental and physical health, but individuals often disengage with writing interventions as they struggle to organize their thoughts and emotions. Reflective prompts have been used to provide direction, and large language models (LLMs) have demonstrated the potential to provide tailored guidance. However, current systems often limit users' flexibility to direct their reflections. We thus present ExploreSelf, an LLM-driven application designed to empower users to control their reflective journey, providing adaptive support through dynamically generated questions. Through an exploratory study with 19 participants, we examine how participants explore and reflect on personal challenges using ExploreSelf. Our findings demonstrate that participants valued the flexible navigation of adaptive guidance to control their reflective journey, leading to deeper engagement and insight. Building on our findings, we discuss the implications of designing LLM-driven tools that facilitate user-driven and effective reflection of personal challenges.

Dasom Choi, SoHyun Park, Kyungah Lee et al.

As minimally verbal autistic (MVA) children communicate with parents through few words and nonverbal cues, parents often struggle to encourage their children to express subtle emotions and needs and to grasp their nuanced signals. We present AACessTalk, a tablet-based, AI-mediated communication system that facilitates meaningful exchanges between an MVA child and a parent. AACessTalk provides real-time guides to the parent to engage the child in conversation and, in turn, recommends contextual vocabulary cards to the child. Through a two-week deployment study with 11 MVA child-parent dyads, we examine how AACessTalk fosters everyday conversation practice and mutual engagement. Our findings show high engagement from all dyads, leading to increased frequency of conversation and turn-taking. AACessTalk also encouraged parents to explore their own interaction strategies and empowered the children to have more agency in communication. We discuss the implications of designing technologies for balanced communication dynamics in parent-MVA child interaction.

Jaehoon Kim, Seungwan Jin, Sohyun Park et al.

Detecting implicit hate speech that is not directly hateful remains a challenge. Recent research has attempted to detect implicit hate speech by applying contrastive learning to pre-trained language models such as BERT and RoBERTa, but the proposed models still do not have a significant advantage over cross-entropy loss-based learning. We found that contrastive learning based on randomly sampled batch data does not encourage the model to learn hard negative samples. In this work, we propose Label-aware Hard Negative sampling strategies (LAHN) that encourage the model to learn detailed features from hard negative samples, instead of naive negative samples in random batch, using momentum-integrated contrastive learning. LAHN outperforms the existing models for implicit hate speech detection both in- and cross-datasets. The code is available at https://github.com/Hanyang-HCC-Lab/LAHN

Minki Hong, Eunsoo Lee, Sohyun Park et al.

Prompt design is a primary control interface for large language models (LLMs), yet standard evaluations largely reduce performance to answer correctness, obscuring why a prompt succeeds or fails and providing little actionable guidance. We propose PEEM (Prompt Engineering Evaluation Metrics), a unified framework for joint and interpretable evaluation of both prompts and responses. PEEM defines a structured rubric with 9 axes: 3 prompt criteria (clarity/structure, linguistic quality, fairness) and 6 response criteria (accuracy, coherence, relevance, objectivity, clarity, conciseness), and uses an LLM-based evaluator to output (i) scalar scores on a 1-5 Likert scale and (ii) criterion-specific natural-language rationales grounded in the rubric. Across 7 benchmarks and 5 task models, PEEM's accuracy axis strongly aligns with conventional accuracy while preserving model rankings (aggregate Spearman rho about 0.97, Pearson r about 0.94, p < 0.001). A multi-evaluator study with four models shows consistent relative judgments (pairwise rho = 0.68-0.85), supporting evaluator-agnostic deployment. Beyond alignment, PEEM captures complementary linguistic failure modes and remains informative under prompt perturbations: prompt-quality trends track downstream accuracy under iterative rewrites, semantic adversarial manipulations induce clear score degradation, and meaning-preserving paraphrases yield high stability (robustness rate about 76.7-80.6%). Finally, using only PEEM scores and rationales as feedback, a zero-shot prompt rewriting loop improves downstream accuracy by up to 11.7 points, outperforming supervised and RL-based prompt-optimization baselines. Overall, PEEM provides a reproducible, criterion-driven protocol that links prompt formulation to response behavior and enables systematic diagnosis and optimization of LLM interactions.

Eunkyung Jo, Yuin Jeong, SoHyun Park et al.

Recent large language models (LLMs) offer the potential to support public health monitoring by facilitating health disclosure through open-ended conversations but rarely preserve the knowledge gained about individuals across repeated interactions. Augmenting LLMs with long-term memory (LTM) presents an opportunity to improve engagement and self-disclosure, but we lack an understanding of how LTM impacts people's interaction with LLM-driven chatbots in public health interventions. We examine the case of CareCall -- an LLM-driven voice chatbot with LTM -- through the analysis of 1,252 call logs and interviews with nine users. We found that LTM enhanced health disclosure and fostered positive perceptions of the chatbot by offering familiarity. However, we also observed challenges in promoting self-disclosure through LTM, particularly around addressing chronic health conditions and privacy concerns. We discuss considerations for LTM integration in LLM-driven chatbots for public health monitoring, including carefully deciding what topics need to be remembered in light of public health goals.

Youngseung Jeon, Jaehoon Kim, Sohyun Park et al.

Considerable efforts are currently underway to mitigate the negative impacts of echo chambers, such as increased susceptibility to fake news and resistance towards accepting scientific evidence. Prior research has presented the development of computer systems that support the consumption of news information from diverse political perspectives to mitigate the echo chamber effect. However, existing studies still lack the ability to effectively support the key processes of news information consumption and quantitatively identify a political stance towards the information. In this paper, we present HearHere, an AI-based web system designed to help users accommodate information and opinions from diverse perspectives. HearHere facilitates the key processes of news information consumption through two visualizations. Visualization 1 provides political news with quantitative political stance information, derived from our graph-based political classification model, and users can experience diverse perspectives (Hear). Visualization 2 allows users to express their opinions on specific political issues in a comment form and observe the position of their own opinions relative to pro-liberal and pro-conservative comments presented on a map interface (Here). Through a user study with 94 participants, we demonstrate the feasibility of HearHere in supporting the consumption of information from various perspectives. Our findings highlight the importance of providing political stance information and quantifying users' political status as a means to mitigate political polarization. In addition, we propose design implications for system development, including the consideration of demographics such as political interest and providing users with initiatives.

Jungeun Lee, Kyungah Lee, Inseok Hwang et al.

Social narratives are known to help autistic children understand and navigate social situations through stories. To ensure effectiveness, however, the materials need to be customized to reflect each child's unique behavioral context, requiring considerable time and effort for parents to practice at home. We present AutiHero, a generative AI-based social narrative system for behavioral guidance, which supports parents to create personalized stories for their autistic children and read them together. AutiHero generates text and visual illustrations that reflect their children's interests, target behaviors, and everyday contexts. In a two-week deployment study with 16 autistic child-parent dyads, parents created 218 stories and read an average of 4.25 stories per day, demonstrating a high level of engagement. AutiHero also provided an effective, low-demanding means to guide children's social behaviors, encouraging positive change. We discuss the implications of generative AI-infused tools to empower parents in guiding their children's behaviors, fostering their social learning.

Migyeong Yang, Kyungah Lee, Jinyoung Han et al.

Journaling can potentially serve as an effective method for autistic adolescents to improve narrative skills. However, its text-centric nature and high executive functioning demands present barriers to practice. We present Autiverse, an AI-guided multimodal journaling app for tablets that scaffolds storytelling through conversational prompts and visual supports. Autiverse elicits key details through a stepwise dialogue with peer-like, customizable AI and composes them into an editable four-panel comic strip. Through a two-week deployment study with 10 autistic adolescent-parent dyads, we examine how Autiverse supports autistic adolescents to organize their daily experience and emotion. Autiverse helped them construct coherent narratives, while enabling parents to learn additional details of their child's events and emotions. The customized AI peer created a comfortable space for sharing, fostering enjoyment and a strong sense of agency. We discuss the implications of designing technologies that complement autistic adolescents' strengths while ensuring their autonomy and safety in sharing experiences.

Bokwang Hwang, Seonkyu Lim, Taewoong Kim et al.

We introduce KFinEval-Pilot, a benchmark suite specifically designed to evaluate large language models (LLMs) in the Korean financial domain. Addressing the limitations of existing English-centric benchmarks, KFinEval-Pilot comprises over 1,000 curated questions across three critical areas: financial knowledge, legal reasoning, and financial toxicity. The benchmark is constructed through a semi-automated pipeline that combines GPT-4-generated prompts with expert validation to ensure domain relevance and factual accuracy. We evaluate a range of representative LLMs and observe notable performance differences across models, with trade-offs between task accuracy and output safety across different model families. These results highlight persistent challenges in applying LLMs to high-stakes financial applications, particularly in reasoning and safety. Grounded in real-world financial use cases and aligned with the Korean regulatory and linguistic context, KFinEval-Pilot serves as an early diagnostic tool for developing safer and more reliable financial AI systems.

John Kalung Leung, Igor Griva, William G. Kennedy et al.

This paper presents an innovative approach to address the problems researchers face in Emotion Aware Recommender Systems (EARS): the difficulty and cumbersome collecting voluminously good quality emotion-tagged datasets and an effective way to protect users' emotional data privacy. Without enough good-quality emotion-tagged datasets, researchers cannot conduct repeatable affective computing research in EARS that generates personalized recommendations based on users' emotional preferences. Similarly, if we fail to fully protect users' emotional data privacy, users could resist engaging with EARS services. This paper introduced a method that detects affective features in subjective passages using the Generative Pre-trained Transformer Technology, forming the basis of the Affective Index and Affective Index Indicator (AII). Eliminate the need for users to build an affective feature detection mechanism. The paper advocates for a separation of responsibility approach where users protect their emotional profile data while EARS service providers refrain from retaining or storing it. Service providers can update users' Affective Indices in memory without saving their privacy data, providing Affective Aware recommendations without compromising user privacy. This paper offers a solution to the subjectivity and variability of emotions, data privacy concerns, and evaluation metrics and benchmarks, paving the way for future EARS research.