Selected Publications

Tracing Logit Trajectories Across Layer Depth: Dataset-Level Explainability for Language Models

Perceptual Hallucination in Vision–Language Models: Definition, Analysis and Verification

Empirical Analysis of Task Mixture Effects in Instruction Tuning: A Statistical Approach

R-GDA: Reflective Guidance Data Augmentation with Multi-Agent Feedback for Domain-Specific Named Entity Recognition

When Does Auxiliary Modality Matter in Solving Geometric Problems? A Comprehensive Study of Textual, Formal, and Visual Modalities

ZEBRA: Leveraging Model-Behavioral Knowledge for Zero-Annotation Preference Dataset Construction

AMACE: Automatic Multi-Agent Chart Evolution for Iteratively Tailored Chart Generation

An Analysis of the Impact of Problem Paraphrasing on LLM-Based Mathematical Problem Solving

FEAT: A Preference Feedback Dataset through a Cost-Effective Auto-Generation and Labeling Framework for English AI Tutoring

Courtroom-LLM: A Legal-Inspired Multi-LLM Framework for Resolving Ambiguous Text Classifications

Does Incomplete Syntax Influence Korean Language Model? Focusing on Word Order and Case Markers

Exploring Domain Robust Lightweight Reward Models based on Router Mechanism

Guidance-Based Prompt Data Augmentation in Specialized Domains for Named Entity Recognition

Absorption Distribution Metabolism Excretion and Toxicity Property Prediction Utilizing a Pre-Trained Natural Language Processing Model and Its Applications in Early-Stage Drug Development

Semantic Ambiguity Detection in Sentence Classification using Task-Specific Embeddings

Interactive User Interface for Dialogue Summarization

Controllable Text Generation using Semantic Control Grammar