Seungyeon Back

Hanyang University

Visiting Student @ Carnegie Mellon University

Pittsburgh, PA, USA

M.S. student in Artificial Intelligence at Hanyang University, advised by Prof. Dong-Kyu Chae. B.S. in Mathematics (minors in Big Data Convergence and Biomedical Engineering), graduated Cum Laude.

My research interests include LLM Reasoning, LLM Agent, and RAG (Retrieval-Augmented Generation). I am a co-first author of AdapDict, a level- and domain-adaptive educational dictionary and encyclopedia system built on LLMs, accepted to CSCW 2026. I am currently working on a graph-based recommendation system in collaboration with LG Electronics, developing dual-graph retrieval pipelines and LLM-based path reasoning for explainable, real-time content recommendation.

I am currently a visiting student at Carnegie Mellon University (Aug 2026 – Feb 2027).

news

Sep 12, 2026	Our project JoyWalk won Best Use of API (Vultr) at HackCMU 2026!
Jan 15, 2026	Our paper AdapDict was accepted to CSCW 2026! (Co-first author)

selected publications

CSCW
AdapDict: A Level- and Domain-Adaptive Educational Dictionary and Encyclopedia System

Manhwi Han, SeungYeon Back, and Dong-Kyu Chae

In Proceedings of the ACM on Human-Computer Interaction (CSCW), 2026

Accepted; Co-first author

Abs Bib PDF Code Website

We propose a level- and domain-adaptive explanation framework for controllable explanation generation in LLMs. A generator-verifier loop with structured outputs reduces hallucination by 50%, and a user-adaptive prompting mechanism enables multi-dimensional control of explanation difficulty. A user study (n=41) demonstrates improved clarity, usability, and domain-specific understanding over baseline tools.
@inproceedings{adapdict2026, title = {AdapDict: A Level- and Domain-Adaptive Educational Dictionary and Encyclopedia System}, author = {Han, Manhwi and Back, SeungYeon and Chae, Dong-Kyu}, booktitle = {Proceedings of the ACM on Human-Computer Interaction (CSCW)}, year = {2026}, note = {Accepted; Co-first author}, }
IEEE Access
An Empirical Study of the Clustering of Mountain Hiking GPS Trajectory Data

SeungYeon Back, Manhwi Han, Dong-Kyu Chae, and 1 more author

IEEE Access, 2026

Under revision; Co-first author

Abs Bib

We propose a novel trajectory similarity measure integrating spatial, temporal, and velocity components for irregular spatio-temporal data, along with an epsilon-ball-based spatial similarity metric and a data-adaptive weighting framework (alpha, beta, gamma). Hierarchical clustering is applied to large-scale GPS trajectory data to uncover latent behavioral patterns.
@article{gpshiking2026, title = {An Empirical Study of the Clustering of Mountain Hiking GPS Trajectory Data}, author = {Back, SeungYeon and Han, Manhwi and Chae, Dong-Kyu and Park, Seoncheol}, journal = {IEEE Access}, year = {2026}, note = {Under revision; Co-first author}, }