Papers by Jean Seo
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. |
MoFE: Mixture of Frozen Experts Architecture (2025.naacl-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are characterized by their immense size, often consisting of at least one billion parameters. |
| Approach: | They propose a mixture of Frozen Experts architecture that integrates PEFT and MoE to enhance both training efficiency and model scalability. |
| Outcome: | The proposed architecture outperforms other methods while achieving the highest efficiency. |
Format Inertia: A Failure Mechanism of LLMs in Medical Pre-Consultation (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models have brought significant improvements to various service domains, including chatbots and medical pre-consultation applications. |
| Approach: | They propose a method that rebalances the turn-count distribution of training data to mitigate Format Inertia in medical pre-consultation tasks. |
| Outcome: | The proposed method significantly alleviates Format Inertia in medical pre-consultation tasks. |
Taxonomy of Comprehensive Safety for Clinical Agents (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing methods for ensuring safety in clinical chatbot applications are not suitable for clinical applications. |
| Approach: | They propose a fine-grained taxonomy that integrates safety filtering and tool selection into a single user intent classification step. |
| Outcome: | The proposed taxonomy integrates safety filtering and tool selection into a single user intent classification step. |
Evaluating the Pre-Consultation Ability of LLMs using Diagnostic Guidelines (2026.eacl-industry)
Copied to clipboard
Jean Seo, Gibaeg Kim, Kihun Shin, Seungseop Lim, Hyunkyung Lee, Wooseok Han, Jongwon Lee, Eunho Yang
| Challenge: | EPAG is a benchmark dataset and evaluation pipeline for pre-consultation of large language models. |
| Approach: | They propose a benchmark dataset and framework for evaluating pre-consultation ability of LLMs using diagnostic guidelines. |
| Outcome: | The proposed framework outperforms frontier LLMs in pre-consultation. |
ManNER & ManPOS: Pioneering NLP for Endangered Manchu Language (2024.lrec-main)
Copied to clipboard
| Challenge: | a new study examines the impact of natural language processing (NLP) on the endangered Manchu language. |
| Approach: | They propose to use BiLSTM-CRF, BERT, and mBERT to train transformer-based models on Manchu for NER and POS tagging tasks. |
| Outcome: | The proposed models achieved over 90% F1 score in both NER and POS tasks. |