19 citations · 29 across the 26 of their papers we have counts for
28 papers
Can a System-One LLM Perform Knowledge Tracing When Few or No Learners Are Logged?
Unggi Lee, Haeun Park
Knowledge tracing (KT) models need many logged learners, so a new course or platform starts without a usable model. In LLM-based KT the LLM generates the answer, which we call Syst…
SpecialEduBench: Benchmarking Vision-Language Models on Knowledge, Skill, and Attitude in Language Intervention for Autistic Children
Jihoi Na, Taeyeong Kim, Sungjune Kong +11
Language is the target of most early intervention for autistic children. Because the goal and the method change from child to child, the work falls to a teacher who takes one child…
EduClaw-Bench: A Long-Horizon Benchmark for Pedagogical LLM Agents with Simulated Learners
Unggi Lee, Sookbun Lee, Yeil Jeong +3
Large language models (LLMs) power educational applications from tutoring to essay scoring, but each is a point solution to a single task, and only recently have these point soluti…
Not the Dimension, the Norm: What Matters in Gradient-Free Weight Perturbation of Language Models
Taeyeong Kim, Ahhyun Kim, TaeHyeon Kim +1
Adapting a language model to a task no longer requires training all of its weights, and a line of parameter-efficient methods has driven the trainable count from billions down to a…
Reinforcement Learning for Special Education: Aligning LLM Tutors to Diverse Learners through Disability-Adaptive Training
Unggi Lee, Jihoi Na, Yeil Jeong +2
Large language models are increasingly deployed as intelligent tutors, yet research on aligning them for special education remains absent. Recent work has applied reinforcement lea…
The Tutoring Effectiveness Index: Predicting LLM Math Tutor Quality from Four Conversation Signals
Shim Jaechang, Unggi Lee
Aligning large language models (LLMs) as math tutors typically demands costly reinforcement-learning (RL) training and external LLM judges. We ask whether a frozen model's internal…
BuddyBench: A Privacy-Constrained Multi-Task Benchmark for Pediatric Social-Communication Personalization
Jeyeon Eo, Joo Young Kim, Ran Ju +2
BuddyBench introduces a privacy-constrained multi-task benchmark for pediatric social-communication personalization. Unlike existing neurodevelopmental repositories that primarily…
LLMs Are Already Good Tutors: Training-Free Prompt Optimization for Pedagogical Math Tutoring
Unggi Lee, Minchul Shin, Yeil Jeong +5
Aligning LLMs for math tutoring typically requires RL-based training with multi-GPU infrastructure. We investigate whether training-free prompt optimization-evolving only the syste…
Are Video Models Zero-Shot Learners and Reasoners in Education? EduVideoBench, A Knowledge-Skills-Attitude Benchmark for Educational Video Generation
Unggi Lee, Hoyoung Ahn, Yoon Choi +16
Video generation models (VGMs) are rapidly entering classrooms, yet existing benchmarks evaluate only perceptual quality, intrinsic faithfulness, generic safety, or video as a reas…
TeachObs: A Human-Validated Benchmark for Multimodal Teaching Observation and Model Evaluation
Yeil Jeong, Youngjin Yoo, Jiyoung Bae +5
Classroom videos contain observable teaching practices, but their pedagogical and visual signals are rarely organized in forms suitable for model evaluation. We present \textit{Tea…
ISD-Agent-Bench: A Comprehensive Benchmark for Evaluating LLM-based Instructional Design Agents
YoungHoon Jeon, Suwan Kim, Haein Son +3
Large Language Model (LLM) agents have shown promising potential in automating Instructional Systems Design (ISD), a systematic approach to developing educational programs. However…
Llama-Polya: Instruction Tuning for Large Language Model based on Polya's Problem-solving
Unggi Lee, Yeil Jeong, Chohui Lee +4
This paper introduces Llama-Polya, an instruction-tuned large language model that integrates Polya's four-step problem-solving framework into its dialogue structure to support math…
Exploring the Role of Automated Feedback in Programming Education: A Systematic Literature Review
Yeonji Jung, Yunseo Lee, Jiyeong Bae +4
Automated feedback systems have become increasingly integral to programming education, where learners engage in iterative cycles of code construction, testing, and refinement. Desp…
Rewarding How Models Think Pedagogically: Integrating Pedagogical Reasoning and Thinking Rewards for LLMs in Education
Unggi Lee, Jiyeong Bae, Jaehyeon Park +7
Large language models (LLMs) are increasingly deployed as intelligent tutoring systems, yet research on optimizing LLMs specifically for educational contexts remains limited. Recen…
OpenLearnLM Benchmark: A Unified Framework for Evaluating Knowledge, Skill, and Attitude in Educational Large Language Models
Unggi Lee, Sookbun Lee, Heungsoo Choi +11
Large Language Models are increasingly deployed as educational tools, yet existing benchmarks focus on narrow skills and lack grounding in learning sciences. We introduce OpenLearn…
Pedagogical Alignment for Vision-Language-Action Models: A Comprehensive Framework for Data, Architecture, and Evaluation in Education
Unggi Lee, Jahyun Jeong, Sunyoung Shin +12
Science demonstrations are important for effective STEM education, yet teachers face challenges in conducting them safely and consistently across multiple occasions, where robotics…
A Training-Free Large Reasoning Model-based Knowledge Tracing Framework for Unified Prediction and Prescription
Unggi Lee, Joo Young Kim, Ran Ju +2
Knowledge Tracing (KT) aims to estimate a learner's evolving mastery based on interaction histories. Recent studies have explored Large Language Models (LLMs) for KT via autoregres…
Pedagogy-R1: Pedagogically-Aligned Reasoning Model with Balanced Educational Benchmark
Unggi Lee, Jaeyong Lee, Jiyeong Bae +6
Recent advances in large reasoning models (LRMs) show strong performance in structured domains such as mathematics and programming; however, they often lack pedagogical coherence a…
How Can Video Generative AI Transform K-12 Education? Examining Teachers' Perspectives through TPACK and TAM
Unggi Lee, Yeil Jeong, Seungha Kim +4
The rapid advancement of generative AI technology, particularly video generative AI (Video GenAI), has opened new possibilities for K-12 education by enabling the creation of dynam…
Echo-Teddy: Preliminary Design and Development of Large Language Model-based Social Robot for Autistic Students
Unggi Lee, Hansung Kim, Juhong Eom +9
Autistic students often face challenges in social interaction, which can hinder their educational and personal development. This study introduces Echo-Teddy, a Large Language Model…
ES-KT-24: A Multimodal Knowledge Tracing Benchmark Dataset with Educational Game Playing Video and Synthetic Text Generation
Dohee Kim, Unggi Lee, Sookbun Lee +5
This paper introduces ES-KT-24, a novel multimodal Knowledge Tracing (KT) dataset for intelligent tutoring systems in educational game contexts. Although KT is crucial in adaptive…
How to Align Large Language Models for Teaching English? Designing and Developing LLM based-Chatbot for Teaching English Conversation in EFL, Findings and Limitations
Jaekwon Park, Jiyoung Bae, Unggi Lee +7
This study investigates the design, development, and evaluation of a Large Language Model (LLM)-based chatbot for teaching English conversations in an English as a Foreign Language…
From Prediction to Application: Language Model-based Code Knowledge Tracing with Domain Adaptive Pre-Training and Automatic Feedback System with Pedagogical Prompting for Comprehensive Programming Education
Unggi Lee, Jiyeong Bae, Yeonji Jung +9
Knowledge Tracing (KT) is a critical component in online learning, but traditional approaches face limitations in interpretability and cross-domain adaptability. This paper introdu…
Language Model Can Do Knowledge Tracing: Simple but Effective Method to Integrate Language Model and Knowledge Tracing Task
Unggi Lee, Jiyeong Bae, Dohee Kim +6
Knowledge Tracing (KT) is a critical task in online learning for modeling student knowledge over time. Despite the success of deep learning-based KT models, which rely on sequences…