publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2025

  1. How does a Language-Specific Tokenizer affect LLMs?
    Jean Seo, Jaeyoon Kim, SungJoo Byun, and 1 more author
    2025
    arXiv
  2. Domain-Expert RAG
    Trustworthy Answers, Messier Data: Bridging the Gap in Low-Resource Retrieval-Augmented Generation for Domain Expert Systems
    Nayoung Choi, Grace Byun, Andrew Chung, and 3 more authors
    2025
    arXiv

2024

  1. KIT-19: A Comprehensive Korean Instruction Toolkit on 19 Tasks for Fine-Tuning Korean Large Language Models
    Dongjun Jang, Sungjoo Byun, Hyemi Jo, and 1 more author
    2024
    arXiv
  2. A Study on How Attention Scores in the BERT Model are Aware of Lexical Categories in Syntactic and Semantic Tasks on the GLUE Benchmark
    Dongjun Jang, Sungjoo Byun, and Hyopil Shin
    2024
    arXiv
  3. CARBD-Ko: A Contextually Annotated Review Benchmark Dataset for Aspect-Level Sentiment Classification in Korean
    Dongjun Jang, Jean Seo, Sungjoo Byun, and 3 more authors
    2024
    arXiv
  4. ManWav: The First Manchu ASR Model
    Jean Seo, Minha Kang, Sungjoo Byun, and 1 more author
    2024
    arXiv
  5. Korean Bio-Medical Corpus (KBMC) for Medical Named Entity Recognition
    Sungjoo Byun, Jiseung Hong, Sumin Park, and 5 more authors
    2024
    arXiv
  6. Detoxification
    Large Language Model Detoxification: Data and Metric Solutions
    SungJoo Byun, and Hyopil Shin
    In NeurIPS 2024 Red Teaming GenAI: What Can We Learn from Adversaries? Workshop, 2024
  7. ManNER & ManPOS: Pioneering NLP for Endangered Manchu Language
    Sangah Lee, Sungjoo Byun, Jean Seo, and 1 more author
    In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 2024

2023

  1. Mergen: The first manchu-korean machine translation model trained on augmented data
    Jean Seo, Sungjoo Byun, Minha Kang, and 1 more author
    2023
    arXiv
  2. DaG LLM ver 1.0: Pioneering Instruction-Tuned Language Modeling for Korean NLP
    Dongjun Jang, Sangah Lee, Sungjoo Byun, and 8 more authors
    2023
    arXiv
  3. Automatic Construction of a Korean Toxic Instruction Dataset for Ethical Tuning of Large Language Models
    Sungjoo Byun, Dongjun Jang, Hyemi Jo, and 1 more author
    2023
    arXiv