Papers by Wooyoung Kim

3 papers
XDAC: XAI-Driven Detection and Attribution of LLM-Generated News Comments in Korean (2025.acl-long)

Copied to clipboard

Challenge: Large language models generate human-like text, raising concerns about their misuse in creating deceptive content.
Approach: They propose a framework for detecting LLM-generated comments in Korean news and introduce a XDAC framework that leverages explainable AI to uncover distinguishing linguistic patterns at token and character levels.
Outcome: The proposed framework outperforms existing methods and achieves 98.5% F1 score in detection and 84.3% F1 in attribution.
TELLME: Test-Enhanced Learning for Language Model Enrichment (2026.findings-eacl)

Copied to clipboard

Challenge: Continual pre-training (CPT) has been widely adopted as a method for domain expansion in large language models, but has faced challenges such as acquiring large-scale domain-specific datasets and high computational costs.
Approach: They propose a method that integrates the Test-Enhanced Learning principle with CPT to promote efficient domain-specific knowledge acquisition and long-term memory retention.
Outcome: The proposed method outperforms existing methods by 23.6% in the financial domain and achieves 9.8% improvement in long-term memory retention.
Korean Disaster Safety Information Sign Language Translation Benchmark Dataset (2024.lrec-main)

Copied to clipboard

Challenge: Sign language is a crucial means of communication for deaf communities.
Approach: They propose to refine Korean sign language translation datasets and release them . they show baseline performance varies depending on tokenization method applied to gloss sequences .
Outcome: The proposed dataset outperforms baseline and spoken language tokenization methods.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations