arXiv subjects

Soohwan Lee

Publications and source records attributed to Soohwan Lee.

10 recordsLinked to original sources

arXiv2026

Investigating LLM-Powered Dissenting Minority Support in Power-Imbalanced Group Decision-Making: Counterargument and Mediation as Intervention Strategies

Minority viewpoints are often suppressed in power-imbalanced group decision-making due to social pressure to comply with the majority. To address this problem, we developed an LLM-powered dissenting minority support system that aimed to foster attention to minority views through either AI-generated counterarguments or AI-mediated messages. We conducted a mixed-method experiment with 96 participants in 24 groups, comparing minority members' experiences across baseline, AI-counterargument, and AI-mediated message conditions. Our findings revealed a nuanced trade-off: AI-generated counterarguments fostered a more flexible atmosphere and enhanced satisfaction, while AI-mediated messaging increased minority participation but unexpectedly reduced their psychological safety. This research contributes empirical evidence on how different AI implementations affect group dynamics, identifies a critical support paradox between participation and psychological safety, provides design implications for future systems, and highlights ethical challenges in implementing AI-mediated communication in hierarchical settings. These insights advance understanding of designing more equitable AI support for power-imbalanced group decision-making.

cs.HC↗

arXiv2026

Are Video Models Zero-Shot Learners and Reasoners in Education? EduVideoBench, A Knowledge-Skills-Attitude Benchmark for Educational Video Generation

Video generation models (VGMs) are rapidly entering classrooms, yet existing benchmarks evaluate only perceptual quality, intrinsic faithfulness, generic safety, or video as a reasoning medium, and none assesses whether the outputs are educationally valid. In this work, we present EduVideoBench, the first balanced benchmark in the education domain, grounded in the Knowledge-Skills-Attitude (KSA) framework so that pedagogical adequacy and educational safety are evaluated jointly rather than as ad-hoc quality dimensions. Across five frontier VGMs, our results show substantial room for improvement across knowledge, skills, and attitude before they are classroom-ready. We complement this with a qualitative analysis of expert comments, finding that educational validity is multi-component, where a single misaligned element such as pacing, legibility, or notation can invalidate an otherwise correct video. We hope EduVideoBench will guide the development of VGMs that are pedagogically grounded and safe for the classroom.

cs.CL↗

arXiv2026

Multi-Agent Consensus as a Cognitive Bias Trigger in Human-AI Interaction

As multi-agent AI systems become more common, users increasingly encounter not a single AI voice but a collective one. This shift introduces social dynamics, such as consensus, dissent, and gradual convergence, that can trigger cognitive biases and distort human judgment. We present findings from a controlled experiment (N = 127) comparing three multi-agent configurations: Majority, Minority, and Diffusion. Quantitative results show that majority consensus accelerates opinion change and inflates confidence, consistent with social proof and bandwagon heuristics. Minority dissent slows this process and promotes more deliberative engagement. Qualitative analysis identifies three interpretive trajectories: reinforcing, aligning, and oscillating, shaped by how users interpret agent independence and group dynamics over time. These findings suggest that agent agreement structure, independent of content, functions as a bias-relevant signal in LLM interactions. We hope this work contributes to the Bias4Trust agenda by grounding multi-agent social influence as a concrete and designable source of bias in human-AI interaction.

cs.HC↗

arXiv2026

Rethinking AI-Mediated Minority Support in Power-Imbalanced Group Decision-Making: From Anonymity To Authenticity

AI-mediated Communication (AIMC) systems increasingly aim to protect minority voices by anonymizing or proxying their input, but anonymity and authenticity are not the same construct. This position paper draws on an ongoing empirical study comparing two LLM-powered minority support strategies in hierarchical group decision-making. We found that relaying minority input anonymously through AI increased participation but significantly reduced psychological safety and satisfaction, while generating only autonomous counterarguments improved satisfaction and reduced marginalization. These counterintuitive findings reveal three provocations for AIMC design in hierarchical contexts: the inherent trade-offs among anonymity, authenticity, agency, and accountability; the risk that power asymmetry reverses intended effects; and the need for AI to facilitate group reflection rather than substitute for human responsibility. These findings and provocations are offered as a contribution to the Restoring Human Authenticity in AI-Mediated Communication workshop.

cs.HC↗

arXiv2025

Beyond Individual UX: Defining Group Experience(GX) as a New Paradigm for Group-centered AI

Recent advancements in HCI and AI have predominantly centered on individual user experiences, often neglecting the emergent dynamics of group interactions. This provocation introduces Group Experience(GX) to capture the collective perceptual, emotional, and cognitive dimensions that arise when individuals interact in cohesive groups. We challenge the conventional Human-centered AI paradigm and propose Group-centered AI(GCAI) as a framework that actively mediates group dynamics, amplifies diverse voices, and fosters ethical collective decision-making. Drawing on social psychology, organizational behavior, and group dynamics, we outline a group-centered design approach that balances individual autonomy with collective interests while developing novel evaluative metrics. Our analysis emphasizes rethinking traditional methodologies that focus solely on individual outcomes and advocates for innovative strategies to capture group collaboration. We call on researchers to bridge the gap between micro-level experiences and macro-level impacts, ultimately enriching and transforming collaborative human interactions.

cs.HC↗

arXiv2025

Conversational Agents as Catalysts for Critical Thinking: Challenging Social Influence in Group Decision-making

Group decision-making processes frequently suffer when social influence and power dynamics suppress minority viewpoints, leading to compliance and groupthink. Conversational agents can counteract these harmful dynamics by encouraging critical thinking. This study investigates how LLM-powered devil's advocate systems affect psychological safety, opinion expression, and satisfaction in power-imbalanced group dynamics. We conducted an experiment with 48 participants in 12 four-person groups, each containing three high-power (senior) and one low-power (junior) member. Each group completed decision tasks in both baseline and AI intervention conditions. Results show AI counterarguments fostered a more flexible atmosphere and significantly enhanced both process and outcome satisfaction for all participants, with particularly notable improvements for minority members. Cognitive workload increased slightly, though not significantly. This research contributes empirical evidence on how AI systems can effectively navigate power hierarchies to foster more inclusive decision-making environments, highlighting the importance of balancing intervention frequency, maintaining conversational flow, and preserving group cohesion.

cs.HC↗

arXiv2025

Amplifying Minority Voices: AI-Mediated Devil's Advocate System for Inclusive Group Decision-Making

Group decision-making often benefits from diverse perspectives, yet power imbalances and social influence can stifle minority opinions and compromise outcomes. This prequel introduces an AI-mediated communication system that leverages the Large Language Model to serve as a devil's advocate, representing underrepresented viewpoints without exposing minority members' identities. Rooted in persuasive communication strategies and anonymity, the system aims to improve psychological safety and foster more inclusive decision-making. Our multi-agent architecture, which consists of a summary agent, conversation agent, AI duplicate checker, and paraphrase agent, encourages the group's critical thinking while reducing repetitive outputs. We acknowledge that reliance on text-based communication and fixed intervention timings may limit adaptability, indicating pathways for refinement. By focusing on the representation of minority viewpoints anonymously in power-imbalanced settings, this approach highlights how AI-driven methods can evolve to support more divergent and inclusive group decision-making.

cs.HC↗

arXiv2024

Conversational Agents as Catalysts for Critical Thinking: Challenging Design Fixation in Group Design

This paper investigates the potential of LLM-based conversational agents (CAs) to enhance critical reflection and mitigate design fixation in group design work. By challenging AI-generated recommendations and prevailing group opinions, these agents address issues such as groupthink and promote a more dynamic and inclusive design process. Key design considerations include optimizing intervention timing, ensuring clarity in counterarguments, and balancing critical thinking with designers' satisfaction. CAs can also adapt to various roles, supporting individual and collective reflection. Our work aligns with the "Death of the Design Researcher?" workshop's goals, emphasizing the transformative potential of generative AI in reshaping design practices and promoting ethical considerations. By exploring innovative uses of generative AI in group design contexts, we aim to stimulate discussion and open new pathways for future research and development, ultimately contributing to practical tools and resources for design researchers.

cs.HC↗

arXiv2024

Expanding the Design Space of Computer Vision-based Interactive Systems for Group Dance Practice

Group dance, a sub-genre characterized by intricate motions made by a cohort of performers in tight synchronization, has a longstanding and culturally significant history and, in modern forms such as cheerleading, a broad base of current adherents. However, despite its popularity, learning group dance routines remains challenging. Based on the prior success of interactive systems to support individual dance learning, this paper argues that group dance settings are fertile ground for augmentation by interactive aids. To better understand these design opportunities, this paper presents a sequence of user-centered studies of and with amateur cheerleading troupes, spanning from the formative (interviews, observations) through the generative (an ideation workshop) to concept validation (technology probes and speed dating). The outcomes are a nuanced understanding of the lived practice of group dance learning, a set of interactive concepts to support those practices, and design directions derived from validating the proposed concepts. Through this empirical work, we expand the design space of interactive dance practice systems from the established context of single-user practice (primarily focused on gesture recognition) to a multi-user, group-based scenario focused on feedback and communication.

cs.HC↗

arXiv2011

REFIM: A Practical Interference Management in Heterogeneous Wireless Access Networks

Due to the increasing demand of capacity in wireless cellular networks, the small cells such as pico and femto cells are becoming more popular to enjoy a spatial reuse gain, and thus cells with different sizes are expected to coexist in a complex manner. In such a heterogeneous environment, the role of interference management (IM) becomes of more importance, but technical challenges also increase, since the number of cell-edge users, suffering from severe interference from the neighboring cells, will naturally grow. In order to overcome low performance and/or high complexity of existing static and other dynamic IM algorithms, we propose a novel low-complex and fully distributed IM scheme, called REFIM, in the downlink of heterogeneous multi-cell networks. We first formulate a general optimization problem that turns out to require intractable computation complexity for global optimality. To have a practical solution with low computational and signaling overhead, which is crucial for low-cost small-cell solutions, e.g., femto cells, in REFIM, we decompose it into per-BS problems based on the notion of reference user and reduce feedback overhead over backhauls both temporally and spatially. We evaluate REFIM through extensive simulations under various configurations, including the scenarios from a real deployment of BSs. We show that, compared to the schemes without IM, REFIM can yield more than 40% throughput improvement of cell-edge users while increasing the overall performance by 10~107%. This is equal to about 95% performance of the existing centralized IM algorithm that is known to be near-optimal but hard to implement in practice due to prohibitive complexity. We also present that as long as interference is managed well, the spectrum sharing policy can outperform the best spectrum splitting policy where the number of subchannels is optimally divided between macro and femto cells.

cs.NI↗