arXiv subjects

Seoyoung Kim

Publications and source records attributed to Seoyoung Kim.

At least 19 recordsLinked to original sources

arXiv2026

Supporting Tutors in the Gig Economy with Automated Feedback: A Case Study on Ringle

The rise of online tutoring platforms in the gig economy has made education more scalable, flexible, and on-demand. These platforms rely on learner evaluations as the primary feedback for tutors and platforms. However, such feedback offers limited guidance for tutors' improvement and makes it difficult to monitor tutor quality at scale. To this end, we explored AI-powered automated feedback and how tutors perceive and respond to it. We deployed a research probe on Ringle, a popular online English tutoring platform, that analyzed tutors' lessons and provided automated feedback. We then surveyed 36 tutors about their experience. Our findings reveal that while tutors perceived automated feedback more negatively than learner feedback, they found it useful for self-monitoring and understanding platform expectations, though discrepancies between them often caused confusion. Based on these insights, we propose design considerations for feedback systems for online educational gig platforms.

cs.HC↗

arXiv2026

$f$-Diophantine sets over finite fields via quasi-random hypergraphs from multivariate polynomials

We investigate $f$-Diophantine sets over finite fields via new explicit constructions of families of quasi-random hypergraphs from multivariate polynomials. In particular, our construction not only offers a systematic method for constructing quasi-random hypergraphs but also provides a unified framework for studying various hypergraphs arising from multivariate polynomials over finite fields, including Paley sum hypergraphs, and hypergraphs derived from Diophantine tuples and their generalizations. We derive an asymptotic formula for the number of $k$-Diophantine $m$-tuples, answering a question of Hammonds et al., and study some related questions for $f$-Diophantine sets, extending and improving several recent works. We also sharpen a classical estimate of Chung and Graham on even partial octahedrons in Paley sum hypergraphs.

math.CO↗

arXiv2026

Evolution of Nuclear Star Cluster in Dwarf Galaxy through Mergers and In-Situ Star Formation

Nuclear Star Clusters (NSCs) are dense stellar systems located at the centers of galaxies. Employing Enzo-Abyss, which integrates hydrodynamics with a direct N-body solver, we introduce a simulation capable of resolving the evolution of NSCs within a live galaxy. This includes live dark matter, gaseous dynamics, star formation and feedback, collisional dynamics for star clusters. The evolution of NSCs is typically shaped by two main processes: mergers of star clusters and in-situ star formation. Our simulation enables investigation of the contributions of these mechanisms to the growth of NSCs. This work focuses on the impact of stellar physics and gas content on the growth of NSCs within a dwarf galaxy. To this end, we carry out four simulations, a fiducial simulation, one without supernova feedback, one with low star formation efficiency, and one with higher galactic gas content. This study shows a likelihood that both mergers and in-situ star formation contribute to NSC evolution comparably. In addition, mergers result in disruption of dense gas clumps within star clusters, indicating that in-situ star formation is suppressed when mergers occur. However, the limitations -- such as the lack of individual star physics and limited spatial/particle mass resolution -- hinder drawing a definite conclusion. Nevertheless, with further development, our simulations will serve as a cornerstone that untangles the complex interplay between mergers and in-situ star formation in shaping the structure and mass of NSCs, thereby providing insights into their formation and evolution.

astro-ph.GA↗

arXiv2026

Multiplicative irreducibility of shifted multiplicative subgroups

In a recent breakthrough, Kalmynin resolved conjectures of Lev--Sonn and Sárközy on additive decompositions of multiplicative subgroups of prime fields. In this paper, inspired by a related conjecture of Sárközy, we prove multiplicative analogues of Kalmynin's results. We show that for every proper multiplicative subgroup $G$, the shifted set $(G-1)\setminus\{0\}$ cannot be written as a product set nontrivially, addressing a conjecture of Sárközy. In addition, we prove that no nonzero shift of any coset of a proper multiplicative subgroup is a ratio set of the form $A/A$. Our results substantially sharpen previous theorems of Shkredov and the authors.

math.CO↗

arXiv2026

Authorship Drift: How Self-Efficacy and Trust Evolve During LLM-Assisted Writing

Large language models (LLMs) are increasingly used as collaborative partners in writing. However, this raises a critical challenge of authorship, as users and models jointly shape text across interaction turns. Understanding authorship in this context requires examining users' evolving internal states during collaboration, particularly self-efficacy and trust. Yet, the dynamics of these states and their associations with users' prompting strategies and authorship outcomes remain underexplored. We examined these dynamics through a study of 302 participants in LLM-assisted writing, capturing interaction logs and turn-by-turn self-efficacy and trust ratings. Our analysis showed that collaboration generally decreased users' self-efficacy while increasing trust. Participants who lost self-efficacy were more likely to ask the LLM to edit their work directly, whereas those who recovered self-efficacy requested more review and feedback. Furthermore, participants with stable self-efficacy showed higher actual and perceived authorship of the final text. Based on these findings, we propose design implications for understanding and supporting authorship in human-LLM collaboration.

cs.HC↗

arXiv2026

IntentFlow: Investigating Fluid Dynamics of Intent Communication in Generative AI

Generative AI shifts interaction toward intent-based outcome specification, despite user intents being inherently vague, fluid, and evolving. While a growing body of HCI research has proposed diverse interaction techniques to support this process, there is limited understanding of what the key aspects of intent communication are and how they interplay to shape users' workflows. To bridge this gap, we first conduct a systematic literature review of 46 HCI papers and identify four core aspects of intent communication support: intent articulation, exploration, management, and synchronization. To investigate how these aspects interplay in practice, we developed IntentFlow, a research probe that embodies all four aspects for a writing task, and conducted a comparative study (N=12). Our action-level behavioral analysis reveals that comprehensive support enables verification-driven refinement and progressive intent curation, reduces cognitive effort, and improves users' sense of control and understanding of intent-output alignment. We conclude with design implications for building generative AI systems that support intent communication as a dynamic, iterative process.

cs.HC↗

arXiv2025

Paley-like quasi-random graphs arising from polynomials

Paley graphs and Paley sum graphs are classical examples of quasi-random graphs. In this paper, we provide new constructions of families of quasi-random graphs that behave like Paley graphs but are neither Cayley graphs nor Cayley sum graphs. These graphs give a unified perspective of studying various graphs arising from polynomials over finite fields, such as Paley graphs, Paley sum graphs, and graphs arising from Diophantine tuples and their generalizations. We also obtain lower bounds on the clique and independence numbers of the graphs in these families.

math.CO↗

arXiv2025

Applying the Gricean Maxims to a Human-LLM Interaction Cycle: Design Insights from a Participatory Approach

While large language models (LLMs) are increasingly used to assist users in various tasks through natural language interactions, these interactions often fall short due to LLMs' limited ability to infer contextual nuances and user intentions, unlike humans. To address this challenge, we draw inspiration from the Gricean Maxims--human communication theory that suggests principles of effective communication--and aim to derive design insights for enhancing human-AI interactions (HAI). Through participatory design workshops with communication experts, designers, and end-users, we identified ways to apply these maxims across the stages of the HAI cycle. Our findings include reinterpreted maxims tailored to human-LLM contexts and nine actionable design considerations categorized by interaction stage. These insights provide a concrete framework for designing more cooperative and user-centered LLM-based systems, bridging theoretical foundations in communication with practical applications in HAI.

cs.HC↗

arXiv2025

Less Talk, More Trust: Understanding Players' In-game Assessment of Communication Processes in League of Legends

In-game team communication in online multiplayer games has shown the potential to foster efficient collaboration and positive social interactions. Yet players often associate communication within ad hoc teams with frustration and wariness. Though previous works have quantitatively analyzed communication patterns at scale, few have identified the motivations of how a player makes in-the-moment communication decisions. In this paper, we conducted an observation study with 22 League of Legends players by interviewing them during Solo Ranked games on their use of four in-game communication media (chat, pings, emotes, votes). We performed thematic analysis to understand players' in-context assessment and perception of communication attempts. We demonstrate that players evaluate communication opportunities on proximate game states bound by player expectations and norms. Our findings illustrate players' tendency to view communication, regardless of its content, as a precursor to team breakdowns. We build upon these findings to motivate effective player-oriented communication design in online games.

cs.HC↗

arXiv2025

Multiplicative structure of shifted multiplicative subgroups and its applications to Diophantine tuples

In this paper, we investigate the multiplicative structure of a shifted multiplicative subgroup and its connections with additive combinatorics and the theory of Diophantine equations. Among many new results, we highlight our main contributions as follows. First, we show that if a nontrivial shift of a multiplicative subgroup $G$ contains a product set $AB$, then $|A||B|$ is essentially bounded by $|G|$, refining a well-known consequence of a classical result by Vinogradov. Second, we provide a sharper upper bound of $M_k(n)$, the largest size of a set such that each pairwise product of its elements is $n$ less than a $k$-th power, refining the recent result of Dixit, Kim, and Murty. One main ingredient in our proof is the first non-trivial upper bound on the maximum size of a generalized Diophantine tuple over a finite field. In addition, we determine the maximum size of an infinite family of generalized Diophantine tuples over finite fields with square order, which is of independent interest. We also make significant progress towards a conjecture of Sárközy on the multiplicative decompositions of shifted multiplicative subgroups. In particular, we prove that for almost all primes $p$, the set $\{x^2-1: x \in \mathbb{F}_p^*\} \setminus \{0\}$ cannot be decomposed as the product of two sets in $\mathbb{F}_p$ non-trivially.

math.NT↗

arXiv2024

LearnerVoice: A Dataset of Non-Native English Learners' Spontaneous Speech

Prevalent ungrammatical expressions and disfluencies in spontaneous speech from second language (L2) learners pose unique challenges to Automatic Speech Recognition (ASR) systems. However, few datasets are tailored to L2 learner speech. We publicly release LearnerVoice, a dataset consisting of 50.04 hours of audio and transcriptions of L2 learners' spontaneous speech. Our linguistic analysis reveals that transcriptions in our dataset contain L2S (L2 learner's Spontaneous speech) features, consisting of ungrammatical expressions and disfluencies (e.g., filler words, word repetitions, self-repairs, false starts), significantly more than native speech datasets. Fine-tuning whisper-small.en with LearnerVoice achieves a WER of 10.26%, 44.2% lower than vanilla whisper-small.en. Furthermore, our qualitative analysis indicates that 54.2% of errors from the vanilla model on LearnerVoice are attributable to L2S features, with 48.1% of them being reduced in the fine-tuned model.

cs.CL↗

arXiv2024

Building bridges between Tate conjectures and arithmetic invariants

In this paper, we clarify and build connections between various conjectures largely motivated by the works of Jean-Pierre Serre and John Tate. We closely study the Tate conjecture for algebraic cycles as well as their motivic generalizations along with various links to Nagao's conjecture.

math.AG↗

arXiv2024

Evolution of Star Cluster Within Galaxy using Self-consistent Hybrid Hydro/N-body Simulation

We introduce a GPU-accelerated hybrid hydro/N-body code (Enzo-N) designed to address the challenges of concurrently simulating star clusters and their parent galaxies. This task has been exceedingly challenging, primarily due to the considerable computational time required, which stems from the substantial scale difference between galaxies (~ 0.1 Mpc) and star clusters (~ pc). Yet, this significant scale separation means that particles within star clusters perceive those outside the star cluster in a semi-stationary state. By leveraging this aspect, we integrate the direct N-body code (Nbody6++GPU) into the cosmological (magneto-)hydrodynamic code (Enzo) through the utilization of the semi-stationary background acceleration approximation. We solve the dynamics of particles within star clusters using the direct N-body solver with regularization for few-body interactions, while evolving particles outside -- dark matter, gas, and stars -- using the particle-mesh gravity solver and hydrodynamic methods. We demonstrate that Enzo-N successfully simulates the co-evolution of star clusters and their parent galaxies, capturing phenomena such as core collapse of the star cluster and tidal stripping due to galactic tides. This comprehensive framework opens up new possibilities for studying the evolution of star clusters within galaxies, offering insights that were previously inaccessible.

astro-ph.GA↗

arXiv2024

Understanding Users' Dissatisfaction with ChatGPT Responses: Types, Resolving Tactics, and the Effect of Knowledge Level

Large language models (LLMs) with chat-based capabilities, such as ChatGPT, are widely used in various workflows. However, due to a limited understanding of these large-scale models, users struggle to use this technology and experience different kinds of dissatisfaction. Researchers have introduced several methods, such as prompt engineering, to improve model responses. However, they focus on enhancing the model's performance in specific tasks, and little has been investigated on how to deal with the user dissatisfaction resulting from the model's responses. Therefore, with ChatGPT as the case study, we examine users' dissatisfaction along with their strategies to address the dissatisfaction. After organizing users' dissatisfaction with LLM into seven categories based on a literature review, we collected 511 instances of dissatisfactory ChatGPT responses from 107 users and their detailed recollections of dissatisfactory experiences, which we released as a publicly accessible dataset. Our analysis reveals that users most frequently experience dissatisfaction when ChatGPT fails to grasp their intentions, while they rate the severity of dissatisfaction related to accuracy the highest. We also identified four tactics users employ to address their dissatisfaction and their effectiveness. We found that users often do not use any tactics to address their dissatisfaction, and even when using tactics, 72% of dissatisfaction remained unresolved. Moreover, we found that users with low knowledge of LLMs tend to face more dissatisfaction on accuracy while they often put minimal effort in addressing dissatisfaction. Based on these findings, we propose design implications for minimizing user dissatisfaction and enhancing the usability of chat-based LLM.

cs.HC↗

arXiv2024

Beyond Prompts: Learning from Human Communication for Enhanced AI Intent Alignment

AI intent alignment, ensuring that AI produces outcomes as intended by users, is a critical challenge in human-AI interaction. The emergence of generative AI, including LLMs, has intensified the significance of this problem, as interactions increasingly involve users specifying desired results for AI systems. In order to support better AI intent alignment, we aim to explore human strategies for intent specification in human-human communication. By studying and comparing human-human and human-LLM communication, we identify key strategies that can be applied to the design of AI systems that are more effective at understanding and aligning with user intent. This study aims to advance toward a human-centered AI system by bringing together human communication strategies for the design of AI systems.

cs.HC↗

arXiv2024

Explicit constructions of Diophantine tuples over finite fields

A Diophantine $m$-tuple over a finite field $\mathbb{F}_q$ is a set $\{a_1,\ldots, a_m\}$ of $m$ distinct elements in $\mathbb{F}_{q}^{*}$ such that $a_{i}a_{j}+1$ is a square in $\mathbb{F}_q$ whenever $i\neq j$. In this paper, we study $M(q)$, the maximum size of a Diophantine tuple over $\mathbb{F}_q$, assuming the characteristic of $\mathbb{F}_q$ is fixed and $q \to \infty$. By explicit constructions, we improve the lower bound on $M(q)$. In particular, this improves a recent result of Dujella and Kazalicki by a multiplicative factor.

math.NT↗

arXiv2022

$k$-Diophantine $m$-tuples in Finite Fields

In this paper, we define a $k$-Diophantine $m$-tuple to be a set of $m$ positive integers such that the product of any $k$ distinct positive integers is one less than a perfect square. We study these sets in finite fields $\mathbb{F}_p$ for odd prime $p$ and guarantee the existence of a $k$-Diophantine m-tuple provided $p$ is larger than some explicit lower bound. We also give a formula for the number of 3-Diophantine triples in $\mathbb{F}_p$ as well as an asymptotic formula for the number of $k$-Diophantine $k$-tuples.

math.NT↗

arXiv2021

From the Birch and Swinnerton-Dyer conjecture to Nagao's conjecture

Let $E$ be an elliptic curve over $\mathbb{Q}$ with discriminant $Δ_E$. For primes $p$ of good reduction, let $N_p$ be the number of points modulo $p$ and write $N_p=p+1-a_p$. In 1965, Birch and Swinnerton-Dyer formulated a conjecture which implies $$\lim_{x\to\infty}\frac{1}{\log x}\sum_{\substack{p\leq x\\ p\nmid Δ_{E}}}\frac{a_p\log p}{p}=-r+\frac{1}{2},$$ where $r$ is the order of the zero of the $L$-function $L_{E}(s)$ of $E$ at $s=1$, which is predicted to be the Mordell-Weil rank of $E(\mathbb{Q})$. We show that if the above limit exits, then the limit equals $-r+1/2$. We also relate this to Nagao's conjecture.

math.NT↗