Papers by Dongjun Jang
KIT-19: A Comprehensive Korean Instruction Toolkit on 19 Tasks for Fine-Tuning Korean Large Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Instruction tuning on large language models is an essential process for models to function well and achieve high performance in the specific tasks. |
| Approach: | They propose to use KIT-19 as an instruction dataset for the development of LLM in Korean to demonstrate its effectiveness. |
| Outcome: | The proposed model outperforms existing Korean LLMs. |
Korean Bio-Medical Corpus (KBMC) for Medical Named Entity Recognition (2024.lrec-main)
Copied to clipboard
Sungjoo Byun, Jiseung Hong, Sumin Park, Dongjun Jang, Jean Seo, Minseok Kim, Chaeyoung Oh, Hyopil Shin
| Challenge: | Named Entity Recognition (NER) plays a pivotal role in medical Natural Language Processing (NLP) yet, there is no open-source medical NER dataset specifically for Korean. |
| Approach: | They used ChatGPT to construct an open-source Korean NER dataset . they found 20% increase in medical NER performance compared to general Korean ner datasets. |
| Outcome: | The KBMC dataset shows an impressive 20% increase in medical NER performance compared to models trained on general Korean NER datasets. |
Enhancing Self-Attention via Knowledge Fusion: Deriving Sentiment Lexical Attention from Semantic-Polarity Scores (2024.starsem-1)
Copied to clipboard
| Challenge: | Existing methods to inject lexical features into self-attention mechanisms have shown remarkable performance across various downstream tasks in NLP. |
| Approach: | They propose to inject lexical features into the self-attention mechanism of Transformer-based models by injecting lexicon-based Sentiment Lexical Attention into the attention scores throughout the training process. |
| Outcome: | The proposed method shows significant performance improvements on the NSMC sentiment classification benchmark and is able to perform in out-of-domain tasks. |
A Study on How Attention Scores in the BERT Model Are Aware of Lexical Categories in Syntactic and Semantic Tasks on the GLUE Benchmark (2024.lrec-main)
Copied to clipboard
| Challenge: | In the realm of sentence comprehension, human attention is not evenly distributed across all words, indicating systematic variations in language processing. |
| Approach: | They propose to categorize tokens according to their lexical categories and focus on changes in attention scores among these categories during the fine-tuning process for downstream tasks. |
| Outcome: | The proposed model is based on a GLUE benchmark dataset and demonstrates that it assigns more bias to specific lexical categories irrespective of the task. |
P-CoT: A Pedagogically-motivated Participatory Chain-of-Thought Prompting for Phonological Reasoning in LLMs (2025.findings-acl)
Copied to clipboard
| Challenge: | Using the PhonologyBench benchmark, we assess tasks like rhyme word generation, g2p conversion, and syllable counting. |
| Approach: | They evaluate phonological reasoning in text-based large language models using the PhonologyBench benchmark and a Pedagogically-motivated Participatory Chain-of-Thought prompt. |
| Outcome: | The proposed model achieves up to 52% improvement and surpasses human baselines in certain tasks. |
RCScore: Quantifying Response Consistency in Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Current evaluations of large language models rely on a single instruction template, overlooking models’ sensitivity to instruction style. |
| Approach: | They propose a multi-dimensional framework quantifying how instruction formulation affects model responses by transforming benchmark problems into multiple instruction styles. |
| Outcome: | The proposed framework reveals that instruction style can shift accuracy by 16.7% points. |