arXiv subjects

Yeonju Jang

Publications and source records attributed to Yeonju Jang.

5 recordsLinked to original sources

arXiv2026

Reinforcement Learning for Special Education: Aligning LLM Tutors to Diverse Learners through Disability-Adaptive Training

Large language models are increasingly deployed as intelligent tutors, yet research on aligning them for special education remains absent. Recent work has applied reinforcement learning to LLM tutors, but these methods target a generic learner in a single domain (mathematics) and do not address the cognitive and communicative diversity of learners with disabilities. We introduce \emph{Special-R1}, a framework that extends pedagogical RL to special education through two components: (1) a two-dimensional adaptive system prompt that couples a difficulty-based support level with a disability-specific teaching style across five disability profiles; and (2) a persona-aware Thinking Reward whose judge rubric is conditioned on the learner's disability profile. On a persona-augmented test set of 690 multi-turn dialogues, our full model raises persona-aware Fit from 6.75 (generic baseline) to 8.40 (+1.65) and SPED-rubric Helpfulness from 0.720 to 0.768, leading on the four-component Total (2.911, +0.064 over the runner-up) while remaining within 0.01 of the strongest variant on the out-of-domain OpenLearnLM benchmark (8.53). Ablations show that the Thinking Reward becomes effective only in combination with adaptive prompting, and that residual weakness on specific learning disability in mathematics motivates targeted multimodal extensions.

cs.CY↗

arXiv2026

"My body is not your Porn": Identifying Trends of Harm and Oppression through a Sociotechnical Genealogy of Digital Sexual Violence in South Korea

Ever since the introduction of internet technologies in South Korea, digital sexual violence (DSV) has been a persistent and pervasive problem. Evolving alongside digital technologies, the severity and scale of violence have grown consistently, leading to widespread public concern. In this paper, we present four eras of image-based DSV in South Korea, spanning from the early internet era of the 1990s to the deepfake scandals in the mid-2020s. Drawing from media coverage, legal documents, and academic literature, we elucidate forms and characteristics of DSV cases in each era, tracing how entrenched misogyny is reconfigured and amplified through evolving technologies, alongside shifting legislative measures. Taking a genealogical approach to read prominent cases of different eras, our analysis identifies three constitutive and interconnected dimensions of DSV: (1) the homo-social fabrication of "obscenity", wherein victims' imagery becomes collectively framed as obscene through participatory practices in male-dominant networks; (2) the increasing imperceptibility of violence, as technologies foreclose victims' ability to perceive harm; and (3) the commercialization of abuse through decentralized economic infrastructures. We suggest future directions for CSCW research, and further reflect on the value of the genealogical method in enabling non-linear understanding of DSV as dynamically evolving sociotechnical configurations of harm.

cs.HC↗

arXiv2024

"The Guide Has Your Back": Exploring How Sighted Guides Can Enhance Accessibility in Social Virtual Reality for Blind and Low Vision People

As social VR applications grow in popularity, blind and low vision users encounter continued accessibility barriers. Yet social VR, which enables multiple people to engage in the same virtual space, presents a unique opportunity to allow other people to support a user's access needs. To explore this opportunity, we designed a framework based on physical sighted guidance that enables a guide to support a blind or low vision user with navigation and visual interpretation. A user can virtually hold on to their guide and move with them, while the guide can describe the environment. We studied the use of our framework with 16 blind and low vision participants and found that they had a wide range of preferences. For example, we found that participants wanted to use their guide to support social interactions and establish a human connection with a human-appearing guide. We also highlight opportunities for novel guidance abilities in VR, such as dynamically altering an inaccessible environment. Through this work, we open a novel design space for a versatile approach for making VR fully accessible.

cs.HC↗

arXiv2024

CLST: Cold-Start Mitigation in Knowledge Tracing by Aligning a Generative Language Model as a Students' Knowledge Tracer

Knowledge tracing (KT), wherein students' problem-solving histories are used to estimate their current levels of knowledge, has attracted significant interest from researchers. However, most existing KT models were developed with an ID-based paradigm, which exhibits limitations in cold-start performance. These limitations can be mitigated by leveraging the vast quantities of external knowledge possessed by generative large language models (LLMs). In this study, we propose cold-start mitigation in knowledge tracing by aligning a generative language model as a students' knowledge tracer (CLST) as a framework that utilizes a generative LLM as a knowledge tracer. Upon collecting data from math, social studies, and science subjects, we framed the KT task as a natural language processing task, wherein problem-solving data are expressed in natural language, and fine-tuned the generative LLM using the formatted KT dataset. Subsequently, we evaluated the performance of the CLST in situations of data scarcity using various baseline models for comparison. The results indicate that the CLST significantly enhanced performance with a dataset of fewer than 100 students in terms of prediction, reliability, and cross-domain generalization.

cs.CL↗

arXiv2021

Memory Association Networks

We introduce memory association networks(MANs) that memorize and remember any data. This neural network has two memories. One consists of a queue-structured short-term memory to solve the class imbalance problem and long-term memory to store the distribution of objects, introducing the contents of storing and generating various datasets.

cs.AI↗